{
 "day": "sat",
 "date": "2026-07-09",
 "radar": [
  {
   "id": "http://arxiv.org/abs/2607.06641v1",
   "title": "Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering",
   "summary": "Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-augmented setting and systematically evaluate retrieval and generation choices. We compare dense, sparse, and hybrid retrieval across multiple embedding models and corpus variants, and show that hybrid retrieval consistently improves recall and ranking quality, with chunk length and topic interacting with ranking performance. Providing retrieved context substantially increases multiple-choice accuracy across a diverse set of LLMs, enabling smaller open-weight models to match or outperform larger models used without retrieval, with gains primarily driven by retrieval quality and careful context selection. To assess realistic free-form answering, we introduce a rubric-based LLM-as-a-judge covering faithfulness, completeness, clarity, and factual consistency, and validate it against dual human annotations. Judge-human agreement is strongest for faithfulness and completeness, while factual consistency and clarity are less reliably reproduced, motivating caution when interpreting those dimensions at scale. Overall, our results highlight retrieval as a primary lever for reliable public health QA and provide practical guidance for building and evaluating RAG systems grounded in official guidance.",
   "published": "2026-07-07T14:47:42Z",
   "authors": [
    "Felix Feldman",
    "Joshua Harris",
    "Timothy Laurence",
    "Leo Loman",
    "Ollie Higgins",
    "Fan Grayson"
   ],
   "why": "The paper's systematic evaluation of RAG configurations, retrieval quality, and faithfulness aligns directly with the researcher's focus on RAG pipelines and evaluation methodologies."
  },
  {
   "id": "http://arxiv.org/abs/2607.06544v1",
   "title": "Rethinking Indic AI from a Lens of Cultural Heritage Preservation",
   "summary": "As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent, there is significant interest in studying how AI impacts the linguistic and cultural foundations of this civilization. AI is seen as a ''double-edged sword'' where on the one hand, it can enable access and inclusion for a large population, on the other, it can homogenize worldviews and exclude underrepresented languages and worldviews. In this paper, we try to characterize this problem by addressing the extensive characteristic nature of Indian linguistics and the way they closely connect to cultural practices and worldview. We then perform a longitudinal survey of how Natural Language Processing (NLP) techniques have evolved in this space, tracing the historical development of Indic NLP, covering key milestones, methodological shifts, and resource creation efforts. In addition, the paper also examines the structural and sociolinguistic characteristics of Indian languages, such as rich morphology, complex scripts and grammar rules, diglossia, and large dialectal variation, and explains how these create unique challenges for building AI foundation models. We then discuss the growing role of Indic foundation models and analyze how these models address these long-standing resource and representation gaps. Finally, we propose a research direction called 'Culture Sensing', which re-imagines AI based on hermeneutic reasoning. Culture Sensing aims to address open problems such as ensuring equitable performance across low-resource languages and producing outputs that are culturally meaningful. By bringing together past work, current techniques, and emerging trends, this paper outlines research directions that can guide the next phase of Indic NLP and contribute to the development of more robust and inclusive Indic foundation models.",
   "published": "2026-07-07T17:51:10Z",
   "authors": [
    "Aparna Madva",
    "Sharath Srivatsa",
    "Srinath Srinivasa",
    "Tulika Saha"
   ],
   "why": "The paper addresses the intersection of linguistic diversity, cultural preservation, and the challenges of building AI for complex, underrepresented languages, which aligns with the researcher's focus on Indigenous language sovereignty and low-resource NLP."
  },
  {
   "id": "http://arxiv.org/abs/2607.06327v1",
   "title": "Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs",
   "summary": "Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale evaluation of UE methods across 22 languages, spanning high-, mid-, and low-resource settings. Using two human-curated Q\\&A datasets, we compare open and closed box UE methods (nine in total) across different model sizes and architectures while eliciting long-form reasoning, avoiding LLM-as-a-judge and embedding-based scoring, which can introduce evaluation noise. We report three main actionable findings. First, we find that prompting models to reason in English while keeping questions in low-resource languages substantially improves UE performance, suggesting that comprehension of low-resource languages is largely intact, and that the reliability bottleneck lies in generation rather than understanding. Second, prompting models to reason in English closes the UE performance gap between low and high-resource languages, demonstrating that generation language matters more than the question language. Third, the choice of UE method should depend on model scale: at smaller scales, open-box probability-based methods outperform alternatives; at larger scales, closed-box self-verbalized uncertainty becomes superior. Finally, we provide an analysis of threshold selection for selective prediction, offering guidance on calibrating abstention in multilingual settings.",
   "published": "2026-07-07T14:25:09Z",
   "authors": [
    "Andrea Alfarano",
    "Andrea Bacciu",
    "Saab Mansour",
    "Amin Mantrach",
    "Marcello Federico"
   ],
   "why": "The paper's findings on how reasoning in English improves performance in low-resource languages directly informs the researcher's work on data-efficient adaptation and reliability in underserved languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.06289v1",
   "title": "From Sinhala to Dhivehi: Cross-Lingual Transfer Learning for Low-Resource Speech Recognition",
   "summary": "Dhivehi, the national language of the Maldives, is currently under-resourced for automatic speech recognition (ASR) and other NLP tasks. This study investigates whether cross-lingual transfer learning from Sinhala, a linguistically related, relatively well-resourced Insular Indo-Aryan language, can improve Dhivehi ASR. We conduct seventeen experiments across five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. However, the adaptation strategy and decoding configuration are equally critical for a successful transfer learning experiment. We conduct seventeen controlled experiments spanning five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control experiment using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. The Turkish control experiment confirms that observed improvements stem from linguistic relatedness; adaptation strategy and decoding configuration are also critical.",
   "published": "2026-07-07T13:57:54Z",
   "authors": [
    "Lukmal Ilyas",
    "Nevidu Jayatilleke"
   ],
   "why": "The paper focuses on cross-lingual transfer learning for low-resource languages, which aligns with the researcher's interest in data-efficient adaptation for underserved languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.05992v1",
   "title": "PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages",
   "summary": "Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.",
   "published": "2026-07-07T08:25:29Z",
   "authors": [
    "Daryna Dementieva",
    "Nikolay Babakov",
    "Kathy H\u00e4mmerl",
    "Ilseyar Alimova",
    "Jind\u0159ich Libovick\u00fd",
    "Shu Okabe"
   ],
   "why": "The paper addresses the gap in mathematical reasoning for underrepresented and low-resource languages, which aligns with the researcher's focus on low-resource NLP and multilingual evaluation."
  },
  {
   "id": "http://arxiv.org/abs/2607.05849v1",
   "title": "CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script",
   "summary": "Low-resource languages remain challenging for machine translation, and Mongolian is a representative case. As a digraphic language, Mongolian is written in both Cyrillic and Traditional scripts, which exhibit a severe imbalance in data availability. While the Cyrillic script is relatively well-resourced, the Traditional script remains extremely data-scarce and orthographically ambiguous, leading to substantial performance degradation in direct translation. We propose CoPiT, a cognitively motivated pivot-based translation pipeline that exploits this internal resource hierarchy by routing translation through the Cyrillic script. The pipeline explicitly resolves script-induced ambiguity in the Traditional script before translation, enabling more stable and accurate meaning transfer. Across multiple backbone models and target languages, CoPiT consistently outperforms direct translation, achieving substantial absolute BLEU improvements together with consistent 1.5-1.6x COMET gains. These gains allow strong open-source models to match or outperform GPT-4.1 under comparable evaluation settings. Beyond inference-time improvements, CoPiT enables the construction of synthetic parallel data directly from Traditional-script text, mitigating data scarcity in realistic low-resource scenarios. We release a new multi-script parallel dataset covering Mongolian in both scripts alongside English, Korean, and Russian. All datasets and code are publicly available at https://anonymous.4open.science/r/anonymous_project-76C7.",
   "published": "2026-07-07T05:12:13Z",
   "authors": [
    "Burte Bayarsaikhan",
    "Serynn Kim",
    "Buru Chang"
   ],
   "why": "The paper addresses low-resource, digraphic language translation and script-induced ambiguity, which aligns with the researcher's focus on underserved orthographies and data-efficient adaptation."
  }
 ],
 "week": [
  {
   "id": "http://arxiv.org/abs/2607.06641v1",
   "title": "Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering",
   "summary": "Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-augmented setting and systematically evaluate retrieval and generation choices. We compare dense, sparse, and hybrid retrieval across multiple embedding models and corpus variants, and show that hybrid retrieval consistently improves recall and ranking quality, with chunk length and topic interacting with ranking performance. Providing retrieved context substantially increases multiple-choice accuracy across a diverse set of LLMs, enabling smaller open-weight models to match or outperform larger models used without retrieval, with gains primarily driven by retrieval quality and careful context selection. To assess realistic free-form answering, we introduce a rubric-based LLM-as-a-judge covering faithfulness, completeness, clarity, and factual consistency, and validate it against dual human annotations. Judge-human agreement is strongest for faithfulness and completeness, while factual consistency and clarity are less reliably reproduced, motivating caution when interpreting those dimensions at scale. Overall, our results highlight retrieval as a primary lever for reliable public health QA and provide practical guidance for building and evaluating RAG systems grounded in official guidance.",
   "published": "2026-07-07T14:47:42Z",
   "authors": [
    "Felix Feldman",
    "Joshua Harris",
    "Timothy Laurence",
    "Leo Loman",
    "Ollie Higgins",
    "Fan Grayson"
   ],
   "why": "The paper's systematic evaluation of RAG configurations, retrieval quality, and faithfulness aligns directly with the researcher's focus on RAG pipelines and evaluation methodologies."
  },
  {
   "id": "http://arxiv.org/abs/2607.06544v1",
   "title": "Rethinking Indic AI from a Lens of Cultural Heritage Preservation",
   "summary": "As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent, there is significant interest in studying how AI impacts the linguistic and cultural foundations of this civilization. AI is seen as a ''double-edged sword'' where on the one hand, it can enable access and inclusion for a large population, on the other, it can homogenize worldviews and exclude underrepresented languages and worldviews. In this paper, we try to characterize this problem by addressing the extensive characteristic nature of Indian linguistics and the way they closely connect to cultural practices and worldview. We then perform a longitudinal survey of how Natural Language Processing (NLP) techniques have evolved in this space, tracing the historical development of Indic NLP, covering key milestones, methodological shifts, and resource creation efforts. In addition, the paper also examines the structural and sociolinguistic characteristics of Indian languages, such as rich morphology, complex scripts and grammar rules, diglossia, and large dialectal variation, and explains how these create unique challenges for building AI foundation models. We then discuss the growing role of Indic foundation models and analyze how these models address these long-standing resource and representation gaps. Finally, we propose a research direction called 'Culture Sensing', which re-imagines AI based on hermeneutic reasoning. Culture Sensing aims to address open problems such as ensuring equitable performance across low-resource languages and producing outputs that are culturally meaningful. By bringing together past work, current techniques, and emerging trends, this paper outlines research directions that can guide the next phase of Indic NLP and contribute to the development of more robust and inclusive Indic foundation models.",
   "published": "2026-07-07T17:51:10Z",
   "authors": [
    "Aparna Madva",
    "Sharath Srivatsa",
    "Srinath Srinivasa",
    "Tulika Saha"
   ],
   "why": "The paper addresses the intersection of linguistic diversity, cultural preservation, and the challenges of building AI for complex, underrepresented languages, which aligns with the researcher's focus on Indigenous language sovereignty and low-resource NLP."
  },
  {
   "id": "http://arxiv.org/abs/2607.06327v1",
   "title": "Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs",
   "summary": "Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale evaluation of UE methods across 22 languages, spanning high-, mid-, and low-resource settings. Using two human-curated Q\\&A datasets, we compare open and closed box UE methods (nine in total) across different model sizes and architectures while eliciting long-form reasoning, avoiding LLM-as-a-judge and embedding-based scoring, which can introduce evaluation noise. We report three main actionable findings. First, we find that prompting models to reason in English while keeping questions in low-resource languages substantially improves UE performance, suggesting that comprehension of low-resource languages is largely intact, and that the reliability bottleneck lies in generation rather than understanding. Second, prompting models to reason in English closes the UE performance gap between low and high-resource languages, demonstrating that generation language matters more than the question language. Third, the choice of UE method should depend on model scale: at smaller scales, open-box probability-based methods outperform alternatives; at larger scales, closed-box self-verbalized uncertainty becomes superior. Finally, we provide an analysis of threshold selection for selective prediction, offering guidance on calibrating abstention in multilingual settings.",
   "published": "2026-07-07T14:25:09Z",
   "authors": [
    "Andrea Alfarano",
    "Andrea Bacciu",
    "Saab Mansour",
    "Amin Mantrach",
    "Marcello Federico"
   ],
   "why": "The paper's findings on how reasoning in English improves performance in low-resource languages directly informs the researcher's work on data-efficient adaptation and reliability in underserved languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.06289v1",
   "title": "From Sinhala to Dhivehi: Cross-Lingual Transfer Learning for Low-Resource Speech Recognition",
   "summary": "Dhivehi, the national language of the Maldives, is currently under-resourced for automatic speech recognition (ASR) and other NLP tasks. This study investigates whether cross-lingual transfer learning from Sinhala, a linguistically related, relatively well-resourced Insular Indo-Aryan language, can improve Dhivehi ASR. We conduct seventeen experiments across five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. However, the adaptation strategy and decoding configuration are equally critical for a successful transfer learning experiment. We conduct seventeen controlled experiments spanning five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control experiment using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. The Turkish control experiment confirms that observed improvements stem from linguistic relatedness; adaptation strategy and decoding configuration are also critical.",
   "published": "2026-07-07T13:57:54Z",
   "authors": [
    "Lukmal Ilyas",
    "Nevidu Jayatilleke"
   ],
   "why": "The paper focuses on cross-lingual transfer learning for low-resource languages, which aligns with the researcher's interest in data-efficient adaptation for underserved languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.05992v1",
   "title": "PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages",
   "summary": "Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.",
   "published": "2026-07-07T08:25:29Z",
   "authors": [
    "Daryna Dementieva",
    "Nikolay Babakov",
    "Kathy H\u00e4mmerl",
    "Ilseyar Alimova",
    "Jind\u0159ich Libovick\u00fd",
    "Shu Okabe"
   ],
   "why": "The paper addresses the gap in mathematical reasoning for underrepresented and low-resource languages, which aligns with the researcher's focus on low-resource NLP and multilingual evaluation."
  },
  {
   "id": "http://arxiv.org/abs/2607.05849v1",
   "title": "CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script",
   "summary": "Low-resource languages remain challenging for machine translation, and Mongolian is a representative case. As a digraphic language, Mongolian is written in both Cyrillic and Traditional scripts, which exhibit a severe imbalance in data availability. While the Cyrillic script is relatively well-resourced, the Traditional script remains extremely data-scarce and orthographically ambiguous, leading to substantial performance degradation in direct translation. We propose CoPiT, a cognitively motivated pivot-based translation pipeline that exploits this internal resource hierarchy by routing translation through the Cyrillic script. The pipeline explicitly resolves script-induced ambiguity in the Traditional script before translation, enabling more stable and accurate meaning transfer. Across multiple backbone models and target languages, CoPiT consistently outperforms direct translation, achieving substantial absolute BLEU improvements together with consistent 1.5-1.6x COMET gains. These gains allow strong open-source models to match or outperform GPT-4.1 under comparable evaluation settings. Beyond inference-time improvements, CoPiT enables the construction of synthetic parallel data directly from Traditional-script text, mitigating data scarcity in realistic low-resource scenarios. We release a new multi-script parallel dataset covering Mongolian in both scripts alongside English, Korean, and Russian. All datasets and code are publicly available at https://anonymous.4open.science/r/anonymous_project-76C7.",
   "published": "2026-07-07T05:12:13Z",
   "authors": [
    "Burte Bayarsaikhan",
    "Serynn Kim",
    "Buru Chang"
   ],
   "why": "The paper addresses low-resource, digraphic language translation and script-induced ambiguity, which aligns with the researcher's focus on underserved orthographies and data-efficient adaptation."
  },
  {
   "id": "http://arxiv.org/abs/2607.05614v1",
   "title": "BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension",
   "summary": "Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due to the scarcity of high-quality annotated data. To address this gap, we introduce BaFCo, a benchmark dataset for Bangla form comprehension with a focus on Document Layout Analysis (DLA) and Key Information Extraction (KIE). BaFCo curates 200 multi-page complex Bangladeshi government forms, sourced from across diverse sectors including agriculture, education, banking, and land management. To accurately capture the structural and contextual complexity of these forms, we define a fine-grained annotation schema comprising 26 types of form entities, along with a separate coarse form entity set consisting of 5 types. We evaluate the latest MLLMs from the ChatGPT, Gemini, Claude, Qwen, and Kimi series using zero-shot and chain-of-thought prompts under both low and high reasoning setups. Our results reveal limitations in current MLLMs' ability in comprehending Bangla forms, particularly in accurately localizing highly granular form entities. Our dataset and code is available at: https://huggingface.co/datasets/Mausul/bafco",
   "published": "2026-07-06T20:17:38Z",
   "authors": [
    "Abu Tyeb Azad",
    "Ishita Sur Apan",
    "Fahim Ahmed",
    "Sumaiya Karim Katha",
    "Ezharuddin Jubaer",
    "Armun Alam"
   ],
   "why": "The paper focuses on low-resource language document understanding and complex layout analysis, which aligns with the researcher's interest in OCR/HTR for underserved orthographies and low-resource NLP."
  },
  {
   "id": "http://arxiv.org/abs/2607.05259v1",
   "title": "SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis",
   "summary": "Sentiment analysis has been a primary domain under Natural Language Processing (NLP) from its inception as it plays a vital role in both real-world and research applications. In high-resource languages, this has been extended a step further, and instead of predicting sentiment at the sentence level, models have been developed to detect more fine-grained sentiments at aspect level. However, in order to conduct this fine-grained Aspect-based Sentiment Analysis (ABSA), datasets annotated with aspects and sentiments toward the said aspects is required. Such datasets are lacking for low-resources languages among which, we can count Sinhala, an Indo-Aryan languages used primarily in Sri Lanka. In this work, we introduce, SalAngaBhava, a new Sinhala Aspect-based Sentiment Analysis dataset which contains Sinhala product reviews that are manually labeled with aspect terms and the associated sentiments (positive, negative, neutral). The data was collected from domain-relevant sources such as user-generated reviews and comments, and was annotated following carefully defined guidelines to ensure consistency and quality. The dataset consists of sentences and aspect-sentiment pairs, encompassing a considerable range of aspects from several domains. The analysis confirms that the dataset is well-structured and sufficiently balanced for ABSA research. This dataset can be used as a benchmark and facilitates further studies related to Sinhala natural language processing, and low-resource sentiment analysis tasks.",
   "published": "2026-07-06T16:05:26Z",
   "authors": [
    "Lakshani Galwatta",
    "Nisansa de Silva",
    "Sarangi Aththanayake",
    "Adithya Galwatta"
   ],
   "why": "The paper addresses low-resource NLP and the creation of high-quality, manually annotated datasets, which aligns with the researcher's focus on data-efficient adaptation and human-in-the-loop annotation."
  },
  {
   "id": "http://arxiv.org/abs/2607.04515v1",
   "title": "Towards Digital Preservation of Efik: TTS for a Low-Resource African Language",
   "summary": "Efik, a tonal language spoken by about 3 million second language speakers and 1.5 million native speakers in Southeastern Nigeria, remains underrepresented in speech synthesis research. We present the first documented end-to-end text-to-speech study for Efik, introducing a curated single speaker corpus of 2,632 utterances totaling three hours and a comparative evaluation of four neural models (VITS, MMS-TTS, SpeechT5, and Orpheus-TTS) under low resource conditions. Native speakers evaluated the systems using MOS, Nat-MOS, and A-MOS. MMS-TTS achieved the highest MOS of 3.80 +/- 0.63 and produced more stable long form speech, though tonal errors persisted. Other models showed greater tonal and prosodic inconsistencies. These results provide a reproducible baseline and highlight the need for larger corpora and tone aware modeling for tonal African languages.",
   "published": "2026-07-05T21:37:15Z",
   "authors": [
    "Offiong Bassey Edet",
    "Emmanuel Oyo-Ita",
    "Archibong Okon Archibong",
    "David Effanga Bassey",
    "Mbuotidem Sunday Awak"
   ],
   "why": "The paper focuses on low-resource speech synthesis for an underrepresented language, which aligns with the researcher's interest in low-resource/endangered-language NLP."
  },
  {
   "id": "http://arxiv.org/abs/2607.03836v1",
   "title": "When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts",
   "summary": "Despite remarkable progress in machine translation, Vision Language Models (VLMs) struggle on historical manuscripts, a domain that stresses core Natural Language Processing (NLP) capabilities: low-resource transliteration, archaic vocabulary, and noisy input signals. We present a systematic framework for evaluating the full image-to-translation pipeline on medieval Latin manuscripts, a setting in which scribal shorthand, ligatures, and parchment degradation expose failure modes that are invisible in clean-text benchmarks. Benchmarking on the CATMuS Latin dataset reveals a specialization gap: domain-specific Optical Character Recognition (OCR) models reduce character error rate by up to 4.3$\\times$ compared to general-purpose VLMs, despite operating at orders of magnitude fewer parameters. We introduce the Interpres-Parallel-Corpus (IPC), a novel dataset comprising 1,383 aligned manuscript image lines, transcriptions, and expert translations, the first of its kind for medieval Latin. Our experiments uncover a complexity paradox: the simplest pipeline, a specialized OCR model feeding directly into a VLM, outperforms all multi-component variants. Adding retrieval-augmented generation (RAG) or post-OCR correction introduces prompt saturation and error propagation that degrade aggregate translation quality. These findings offer both a new benchmark and practical guidance for deploying translation systems in low-resource historical settings.",
   "published": "2026-07-04T11:58:52Z",
   "authors": [
    "Nguyen Kim Hai Bui",
    "Md. Easin Arafat",
    "Tam\u00e1s G\u00e1bor Orosz",
    "Mufti Mahmud"
   ],
   "why": "The paper focuses on low-resource OCR for underserved orthographies and the evaluation of image-to-text pipelines, which directly aligns with the researcher's work on legacy text OCR and faithfulness evaluation."
  },
  {
   "id": "http://arxiv.org/abs/2607.02862v1",
   "title": "Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion",
   "summary": "Automatic Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian languages, many of which are low-resource and exhibit significant dialectal differences. Existing methods often optimize ASR or DID individually, resulting in performance trade-offs. In this work, we propose a multimodal framework that jointly improves ASR and DID. Our method employs a Bottleneck Encoder to extract dialectal features from Conformer-based speech representations and a RoBERTa encoder to process ASR-generated CTC embeddings. A gating mechanism merges these features, followed by an attention encoder to refine the representations. The learned embeddings are concatenated with Conformer outputs to enhance ASR features. Evaluated on eight Indian languages with thirty-three dialects, our method achieves an average DID accuracy of 81.63% and average CER and WER of 4.65% and 17.73%, respectively. These results highlight the effectiveness of our method for joint ASR-DID modeling.",
   "published": "2026-07-03T01:53:05Z",
   "authors": [
    "Saurabh Kumar",
    " Amartyaveer",
    "Prasanta Kumar Ghosh"
   ],
   "why": "The paper addresses low-resource speech processing and dialectal variations, which aligns with the researcher's interest in low-resource/Indigenous speech applications."
  },
  {
   "id": "http://arxiv.org/abs/2607.02763v1",
   "title": "LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering",
   "summary": "Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in low-resource settings. This paper investigates whether text-to-speech (TTS) can provide task-specific training data for Luxembourgish SQA without requiring a large human-recorded QA corpus. Starting from existing text-based QA resources, we translate questions into Luxembourgish, synthesize spoken questions with multiple TTS systems, and pair them with textual answers. We train a parameter-efficient SLAM-style architecture that connects a frozen Whisper encoder to frozen multilingual LLM backends through a learned projector and LoRA adapters. We compare MMS-TTS, Qwen3-TTS, and OmniVoice variants, including single-source corpora of about 48k questions and a 4TTS multi-source mix of approximately 230k questions. Evaluation on LLAMA-LB-Test with two real Luxembourgish speaker conditions shows that multi-source and voice-design-based synthetic training configurations yield the strongest SQA performance. The results also show that no-reference TTS quality scores do not monotonically predict downstream QA performance, indicating that synthetic speech must be evaluated as task-specific training data rather than only as natural-sounding audio.",
   "published": "2026-07-02T21:00:52Z",
   "authors": [
    "Nina Hosseini-Kivanani",
    "Marco Matassoni",
    "Alessio Brutti"
   ],
   "why": "The paper addresses low-resource SQA through data-efficient synthetic augmentation, which aligns with the researcher's focus on low-resource NLP and small-corpus adaptation."
  },
  {
   "id": "http://arxiv.org/abs/2607.05069v1",
   "title": "MIRAGE: Defending Long-Form RAG Against Misinformation Pollution",
   "summary": "Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but real-world retrieval is often polluted: semantically relevant passages may contain subtle misinformation, misleading framings, or fabrications. We introduce MIRAGE, a training-free, model-agnostic defense for long-form RAG. MIRAGE builds an NLI-based cross-document claim graph and applies a Defended-Claims Gate to either condition generation on a consistent, multi-source supported subset or to block retrieval and answer parametrically. We also release a minimal-edit pollution protocol spanning four perturbation families (Unambiguous, Conflicting, Misleading, Fabricated) to construct matched clean, mixed, and fully polluted evaluation regimes. Across four long-form QA benchmarks and multiple commercial and open-weight LLMs, pollution severely degrades vanilla RAG, while MIRAGE consistently restores factuality under mixed and fully polluted evidence and outperforms prior robust-RAG methods. Our implementation and datasets are available at https://github.com/SaadElDine/MIRAGE.",
   "published": "2026-07-06T13:36:12Z",
   "authors": [
    "Saadeldine Eletter",
    "Ruihong Zeng",
    "Yuxia Wang",
    "Maxim Panov",
    "Aleksandr Rubashevskii",
    "Preslav Nakov"
   ],
   "why": "The paper's focus on RAG faithfulness and defending against misinformation aligns with the researcher's interest in RAG evaluation and grounding in community-approved sources."
  },
  {
   "id": "http://arxiv.org/abs/2607.04223v1",
   "title": "Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)",
   "summary": "Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why. To close this gap, we introduce Grounding-Aware Sensitivity by Perturbation (GASP), a span-level detector that scores each answer sentence by how strongly its likelihood depends on the retrieved evidence, a quantity we term grounding sensitivity. GASP holds the answer fixed and re-scores it under the full context, under no context, and with each chunk removed, then measures the log-likelihood drops and Jensen-Shannon divergences (JSD). The likelihood of a grounded sentence collapses once its supporting passage is removed, whereas a hallucinated sentence is almost unaffected, a contrast we interpret by casting decoding as a random nonlinear iterated function system (RNIFS). We evaluate GASP on three benchmarks (RAGTruth, TofuEval, RAGBench) with three instruction-tuned scorers from two model families (Qwen2.5-0.5B, Qwen2.5-1.5B, and SmolLM2-1.7B) under a leakage-clean protocol. On RAGTruth it reaches a response-level area under the ROC curve (AUC) of about 0.73 and a span-level AUC of about 0.67, improving significantly over perplexity and by clear margins over length, whole-context natural language inference (NLI), and self-consistency baselines. The only baseline competitive at the span level is a well-configured chunk-level entailment verifier, which requires a separate model, whereas a training-free threshold on the grounding features matches the trained classifier without labeled data and serves as the default detector. Beyond RAGTruth, the signal transfers to TofuEval but not to short-answer question answering in RAGBench, showing GASP is best suited to outputs constructed from the retrieved context rather than answers recoverable from parametric knowledge.",
   "published": "2026-07-05T10:35:30Z",
   "authors": [
    "Mohamed Aly Bouke"
   ],
   "why": "The paper's focus on span-level hallucination detection and grounding sensitivity directly supports the researcher's goal of building reliable, faithfulness-evaluated RAG pipelines for low-resource languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.04008v1",
   "title": "Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis",
   "summary": "We present a candidate-constrained retrieval-augmented generation system for LongEval-RAG, where each query is associated with an organizer-provided candidate set and all retrieved evidence and final citations must remain within that set. The system combines deterministic provenance tracking with passage-based retrieval, deterministic query expansion, pseudo-relevance feedback (PRF), reciprocal rank fusion (RRF), lightweight evidence reranking, citation-aware evidence aggregation, and optional MiniLM sentence reranking. We evaluate ten pipeline variants using a primary organizer evaluation and a supplementary self-generated diagnostic protocol. The primary evaluation shows that the strongest balanced variant is rule-minilm: a rule-based chunking pipeline with query expansion, PRF, RRF, reranking, citation prior, and late MiniLM sentence selection. This variant obtains the highest BERTScore, retrieval precision, nugget coverage, and average grade among our submissions. The result suggests that the main gain does not come from more complex semantic or topic-shift chunking, but from pairing stable rule-based evidence units with sentence-level neural selection before generation. The supplementary LLM-judge evaluation remains useful for early diagnosis and additional analysis, but it emphasizes different systems than the primary gold-answer and nugget-based evaluation, highlighting the need for multi-metric RAG evaluation.",
   "published": "2026-07-04T20:07:57Z",
   "authors": [
    "Yingdong Yang",
    "Haijian Wu"
   ],
   "why": "The paper's focus on RAG faithfulness, citation-aware evidence aggregation, and rigorous evaluation protocols directly aligns with the researcher's interest in grounded RAG pipelines and per-stage evaluation."
  },
  {
   "id": "http://arxiv.org/abs/2607.03447v1",
   "title": "TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation",
   "summary": "Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts. Proper evaluation would require instrumenting all pertinent stages: extraction, graph construction, and inference, coherently enough to localize failures, so that a failure at one stage is not discovered as a wrong answer at the end. We introduce TRIAGE, a stage-aware instrumentation framework for automated, document-grounded graph-RAG that asks not only whether the underlying graph can be trusted but at what cost it can be queried. TRIAGE attaches stage-specific, independently interpretable metrics to three stages: the KG Implementation (triple confidence, source coverage, and schema and canonicalization checks), the KG Validation by expert (graph-level structural quality, with correctness and completeness computed only as offline calibration when a reference is available), and the KG Usage (retrieval coverage, faithfulness, and retrieval cost); the deployed metrics need no gold annotations, the gold-requiring ones serving only as offline calibration. At usage time these metrics form a diagnostic chain of necessary conditions whose first broken link localizes the failure, and the diagnosis maps to the stage levers that can remedy it: extraction, graph and schema, or retrieval. TRIAGE is a theoretical framework with a proof of concept and a reproducible evaluation protocol.",
   "published": "2026-07-03T16:01:20Z",
   "authors": [
    "Axel TahmasebiMoradi",
    "Lucas Schott",
    "Martin Royer"
   ],
   "why": "The paper's focus on stage-aware instrumentation and failure localization in RAG pipelines directly aligns with the researcher's interest in per-stage evaluation and faithfulness."
  },
  {
   "id": "http://arxiv.org/abs/2607.02966v1",
   "title": "Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG",
   "summary": "Cross-lingual retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse languages but retrieved passages remain English. In this setting, generation can fail despite strong base models: English evidence induces language drift (English or code-switching outputs) and models use evidence unreliably when producing non-English answers. We attribute these failures to two post-training challenges: (i) errors are prefix-dependent, so fixed-trajectory supervision suffers from prefix mismatch; and (ii) sequence-level (partly discrete / judge-based) rewards yield noisy credit assignment and high-variance updates. We propose TR-RAG, a teacher-regularized RL recipe that couples reward optimization with on-policy distillation on student-visited prefixes. A compact student samples on-policy answers, while a stronger frozen teacher is queried only on those prefixes and provides a prefix-wise student-to-teacher reverse-KL anchor. We further introduce a reward decomposition for English-evidence multilingual generation, combining language consistency, character 3-gram recall, and an LLM-judge score for evidence-grounded correctness. Across three benchmarks -- BioASQ-ENKB5, Hotpot-ENKB5, and naturally multilingual MKQA -- and two backbones, TR-RAG improves the composite of language adherence and evidence-grounded correctness over strong baselines. Crucially, the teacher anchor acts as a safety net: on in-domain languages it prevents the large language-consistency collapses (up to ~27 percentage points) that reward-only RL can suffer by drifting below even the base model, while on distant out-of-distribution languages -- where reward-only RL stalls at the base model's ceiling -- it still improves evidence grounding; and on character 3-gram recall the compact student sometimes surpasses its 70B teacher.",
   "published": "2026-07-03T05:17:48Z",
   "authors": [
    "Haotian Zhou",
    "Weiran Huang",
    "Siqi Liu",
    "Xiting Wang",
    "Xin Zhang",
    "Zhihao Wen"
   ],
   "why": "The paper addresses cross-lingual RAG failures and reward decomposition for evidence-grounded generation, which directly informs the researcher's work on RAG pipelines and faithfulness for low-resource languages."
  },
  {
   "id": "http://arxiv.org/abs/2607.04884v1",
   "title": "HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better",
   "summary": "We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.",
   "published": "2026-07-06T10:06:05Z",
   "authors": [
    "Gengluo Li",
    "Xingyu Wan",
    "Shangpin Peng",
    "Weinong Wang",
    "Hao Feng",
    "Yongkun Du"
   ],
   "why": "The paper addresses ancient-script OCR and low-resource multilingual capabilities through an agentic data construction system, which aligns with the researcher's focus on underserved orthographies and data-efficient adaptation."
  }
 ],
 "episodes_this_week": [
  "Paper of the day \u2014 Rethinking Indic AI from a Lens of Cultural Heritage Preservation",
  "Paper of the day \u2014 When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manu",
  "Paper of the day \u2014 TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation",
  "Research radar \u2014 20260709",
  "Paper of the day \u2014 LakotaBERT: A Transformer-based Model for Low Resource Lakota"
 ]
}