From Phonemes to Meaning: Evaluating Large Language Models on Tamil

• URL: http://arxiv.org/abs/2511.12387v1
• Date: Sat, 15 Nov 2025 23:41:16 GMT
• Title: From Phonemes to Meaning: Evaluating Large Language Models on Tamil
• Authors: Jeyarajalingam Varsha, Menan Velayuthan, Sumirtha Karunakaran, Rasan Nivethiga, Kengatharaiyer Sarveswaran,
• Abstract summary: ILAKKANAM is the first Tamil-specific linguistic evaluation benchmark manually curated using 820 questions from Sri Lankan school-level Tamil subject examination papers.<n>Our results show that Gemini 2.5 achieves the highest overall performance, while open-source models lag behind.<n>No strong correlation is observed between a model's overall performance and its ability to identify linguistic categories, suggesting that performance may be driven by exposure rather than genuine understanding.
• Score: 1.0493506909428438
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) have shown strong generalization across tasks in high-resource languages; however, their linguistic competence in low-resource and morphologically rich languages such as Tamil remains largely unexplored. Existing multilingual benchmarks often rely on translated English datasets, failing to capture the linguistic and cultural nuances of the target language. To address this gap, we introduce ILAKKANAM, the first Tamil-specific linguistic evaluation benchmark manually curated using 820 questions from Sri Lankan school-level Tamil subject examination papers. Each question is annotated by trained linguists under five linguistic categories and a factual knowledge category, spanning Grades 1--13 to ensure broad linguistic coverage. We evaluate both closed-source and open-source LLMs using a standardized evaluation framework. Our results show that Gemini 2.5 achieves the highest overall performance, while open-source models lag behind, highlighting the gap in linguistic grounding. Category- and grade-wise analyses reveal that all models perform well on lower-grade questions but show a clear decline as linguistic complexity increases. Further, no strong correlation is observed between a model's overall performance and its ability to identify linguistic categories, suggesting that performance may be driven by exposure rather than genuine understanding.

Related papers

• Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages [0.5949779668853555]
  Large language models (LLMs) are routinely evaluated on language use tasks, yet their knowledge of linguistic structure remains poorly understood.<n>Using accuracy and macro F1, together with majority-class and chance baselines, we analyse overall performance and examine variation by linguistic domains and language-related factors.<n>Our results show that metalinguistic knowledge in current LLMs is limited: GPT-4o performs best but only moderate accuracy (0.367), while open-source models lag behind.
  arXiv  Detail & Related papers  (2026-02-02T14:49:56Z)
• Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish [12.286855282078305]
  GPT-4o, GPT-4, Claude3.5Sonnet, LLaMA3.1, MistralLarge2, LLaMA-2Chat13B, and Mistral7BInstruct are evaluated.<n>Our benchmark spans four diverse tasks: open-domain question answering, document summarization, English-to-X translation, and culturally grounded dialogue.
  arXiv  Detail & Related papers  (2025-11-05T22:09:53Z)
• ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models [4.615257892219717]
  We introduce ChiKhaPo, consisting of 8 subtasks of varying difficulty designed to evaluate the lexical comprehension and generation abilities of generative models.<n>ChiKhaPo draws on existing lexicons, monolingual data, and bitext, and provides coverage for 2700+ languages for 2 subtasks, surpassing any existing benchmark in terms of language coverage.
  arXiv  Detail & Related papers  (2025-10-19T16:55:20Z)
• Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
  Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
  arXiv  Detail & Related papers  (2025-05-23T02:46:18Z)
• Crosslingual Reasoning through Test-Time Scaling [51.55526326294275]
  We find that scaling up inference compute for English-centric reasoning language models (RLMs) improves multilingual mathematical reasoning across many languages.<n>While English-centric RLM's CoTs are naturally predominantly English, they consistently follow a quote-and-think pattern to reason about quoted non-English inputs.<n>We observe poor out-of-domain reasoning generalization, in particular from STEM to cultural commonsense knowledge, even for English.
  arXiv  Detail & Related papers  (2025-05-08T16:50:06Z)
• PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts [85.78821098963607]
  PolyMath is a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels.<n>Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation.
  arXiv  Detail & Related papers  (2025-04-25T15:39:04Z)
• How does a Multilingual LM Handle Multiple Languages? [0.0]
  This study critically examines capabilities in multilingual understanding, semantic representation, and cross-lingual knowledge transfer.<n>It assesses semantic similarity by analyzing multilingual word embeddings for consistency using cosine similarity.<n>It examines BLOOM-1.7B and Qwen2 through Named Entity Recognition and sentence similarity tasks to understand their linguistic structures.
  arXiv  Detail & Related papers  (2025-02-06T18:08:14Z)
• MILU: A Multi-task Indic Language Understanding Benchmark [7.652738829153342]
  We introduce MILU, a comprehensive evaluation benchmark designed to assess Large Language Models in Indic languages.<n>With an India-centric design, MILU incorporates material from regional and state-level examinations, covering topics such as local history, arts, festivals, and laws, alongside standard subjects like science and mathematics.<n>Open multilingual models outperform language-specific fine-tuned models, which perform only slightly better than random baselines.
  arXiv  Detail & Related papers  (2024-11-04T19:17:17Z)
• Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings [12.507989493130175]
  Large language models (LLMs) have garnered significant interest in natural language processing (NLP) Recent studies have highlighted the limitations of LLMs in low-resource languages. We present datasets for sentiment and hate speech tasks by translating from English to Bangla, Hindi, and Urdu.
  arXiv  Detail & Related papers  (2024-08-05T05:09:23Z)
• Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
  We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence. We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena. As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
  arXiv  Detail & Related papers  (2024-04-29T17:58:36Z)
• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.