{
 "day": "thu",
 "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."
  }
 ],
 "news": [
  {
   "title": "Google Maps launches New Zealand voice to improve te reo M\u0101ori pronunciation",
   "url": "https://www.rnz.co.nz/news/te-ao-maori/653541/google-launches-improved-pronunciation-tool-for-te-reo-maori-place-names",
   "summary": "Google partnered with Te Taura Whiri i te Reo M\u0101ori (the M\u0101ori Language Commission) to roll out a new AI text-to-speech voice for Google Maps that correctly pronounces te reo M\u0101ori city and town names, addressing years of mispronunciation complaints. The voice was trained on a Kiwi speaker over roughly six months and is rolling out over two weeks, with streets and roads planned for a future update. Te Taura Whiri chief executive Ngahiwi Apanui-Barr called it a step toward securing te reo M\u0101ori's future in the digital age.",
   "published": "2026-07-03"
  },
  {
   "title": "Navajo man creates mobile app to offer tourists a Native lens on historic routes",
   "url": "https://www.kunm.org/local-news/2026-07-02/navajo-man-mobile-app-tourists-native-lens-historic-routes-tribal-trailz-route-66-route66",
   "summary": "George R. Joe, a Navajo former educator, spent three years building 'Tribal Trailz,' a GPS-activated audio tour app covering routes like Gallup-to-Flagstaff and Flagstaff-to-Phoenix. As users drive, the app narrates cultural and historical context about Navajo, Zuni, and Acoma lands and landmarks, aiming to correct tourist misconceptions about Native peoples. Joe is in phase two of development, adding segments for Albuquerque and Santa Fe.",
   "published": "2026-07-02"
  },
  {
   "title": "AI must be built with Indigenous Knowledges, not against them",
   "url": "https://phys.org/news/2026-07-ai-built-indigenous-knowledges.html",
   "summary": "Published as Australia marked 50 years of NAIDOC Week, this piece argues AI risks becoming another extractive force toward Indigenous Knowledges unless built on consent, credit, and return. It cites Aboriginal medical clinics in regional Western Australia trialing AI-assisted diabetic retinopathy screening as an example of AI done well, and calls for embedding Indigenous Knowledge Systems and Indigenous Data Sovereignty (CARE/OCAP) as mandatory foundations rather than ethical add-ons.",
   "published": "2026-07-04"
  },
  {
   "title": "Three Sovereignties, One AI: State, Corporate, and Indigenous Techno-Sovereignty",
   "url": "https://moderndiplomacy.eu/2026/07/08/three-sovereignties-one-ai-state-corporate-and-indigenous-techno-sovereignty/",
   "summary": "This analysis frames AI-era sovereignty as a three-way contest between state, corporate, and Indigenous actors, arguing traditional Westphalian sovereignty concepts fail to capture how AI power flows through corporate-controlled infrastructure. It points to Te Hiku Media's 92%-accurate Te Reo M\u0101ori speech recognition model and the First Languages AI Reality project as examples of Indigenous techno-sovereignty in practice, and calls for federated architectures, data trusts, and permanent Indigenous representation in AI standards bodies.",
   "published": "2026-07-08"
  },
  {
   "title": "Participation Without Power: Technology Sovereignty, Data Sovereignty and the AI Divide in South Asia",
   "url": "https://codata.org/participation-without-power-technology-sovereignty-data-sovereignty-and-the-ai-divide-in-south-asia/",
   "summary": "An online side event to the UN Global Dialogue on AI Governance, held July 6, 2026, examined whether South Asian nations are building genuine sovereign AI capacity or a more sophisticated form of dependency. The discussion specifically addressed how Indigenous and tribal communities' ecological knowledge, territorial records, and oral traditions are entering AI systems without consent across jurisdictions with no clear accountable actor, despite obligations under ILO Convention 169 and UNDRIP.",
   "published": "2026-07-06"
  }
 ]
}