The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian Riddles

• URL: http://arxiv.org/abs/2511.00960v2
• Date: Tue, 04 Nov 2025 14:07:38 GMT
• Title: The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian Riddles
• Authors: Abhinav P M, Ojasva Saxena, Oswald C, Parameswari Krishnamurthy,
• Abstract summary: This paper examines the reasoning and self-assessment abilities of LLMs across seven major Indian languages.<n>We introduce a multilingual riddle dataset combining traditional riddles with context-reconstructed variants.<n>We evaluate five LLMs-Gemini 2.5 Pro, Gemini 2.5 Flash, Mistral-Saba, LLaMA 4 Scout, and LLaMA 4 Maverick-under seven prompting strategies.
• Score: 1.0732935873226022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The extent to which large language models (LLMs) can perform culturally grounded reasoning across non-English languages remains underexplored. This paper examines the reasoning and self-assessment abilities of LLMs across seven major Indian languages-Bengali, Gujarati, Hindi, Kannada, Malayalam, Tamil, and Telugu. We introduce a multilingual riddle dataset combining traditional riddles with context-reconstructed variants and evaluate five LLMs-Gemini 2.5 Pro, Gemini 2.5 Flash, Mistral-Saba, LLaMA 4 Scout, and LLaMA 4 Maverick-under seven prompting strategies. In the first stage, we assess riddle-solving performance and find that while Gemini 2.5 Pro performs best overall, few-shot methods yield only marginal gains, and accuracy varies notably across languages. In the second stage, we conduct a self-evaluation experiment to measure reasoning consistency. The results reveal a key finding: a model's initial accuracy is inversely correlated with its ability to identify its own mistakes. Top-performing models such as Gemini 2.5 Pro are overconfident (4.34% True Negative Rate), whereas lower-performing models like LLaMA 4 Scout are substantially more self-aware (42.09% True Negative Rate). These results point to clear gaps in multilingual reasoning and highlight the need for models that not only reason effectively but also recognize their own limitations.

Related papers

• Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning [71.4175109189942]
  We present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR)<n>This approach designates the model's primary language as the pivot language.<n>It establishes a cross-lingual self-feedback mechanism without relying on external correct answers or reward models.
  arXiv  Detail & Related papers  (2026-01-25T03:20:00Z)
• 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)
• KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino [0.0]
  We present KatotohananQA, a Filipino translation of the TruthfulQA benchmark.<n>Seven free-tier proprietary models were assessed using a binary-choice framework.<n>Findings show a significant performance gap between English and Filipino truthfulness.
  arXiv  Detail & Related papers  (2025-09-07T14:09:57Z)
• MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs [56.87573414161703]
  We introduce the Multilingual Native Reasoning Challenge (MultiNRC), a benchmark to assess Large Language Models (LLMs)<n>MultiNRC covers four core reasoning categories: language-specific linguistic reasoning, wordplay & riddles, cultural/tradition reasoning, and math reasoning with cultural relevance.<n>For cultural/tradition reasoning and math reasoning with cultural relevance, we also provide English equivalent translations of the multilingual questions by manual translation from native speakers fluent in English.
  arXiv  Detail & Related papers  (2025-07-23T12:56:31Z)
• 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)
• SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment [78.4550589538805]
  We propose an efficient multilingual reasoning alignment approach that precisely identifies and fine-tunes the layers responsible for handling multilingualism.<n> Experimental results show that our method, SLAM, only tunes 6 layers' feed-forward sub-layers including 6.5-8% of all parameters within 7B and 13B LLMs.
  arXiv  Detail & Related papers  (2025-01-07T10:29:43Z)
• Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings [12.507989493130175]
  GPT-4, Llama 2, and Gemini are evaluated for their effectiveness in English compared to other low-resource languages from South Asia. Findings suggest GPT-4 outperformed Llama 2 and Gemini in all five prompt settings and across all languages.
  arXiv  Detail & Related papers  (2024-10-17T02:12:30Z)
• Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks [68.33068005789116]
  We introduce ReDial, a benchmark containing 1.2K+ parallel query pairs in Standardized English and AAVE.<n>We evaluate widely used models, including GPT, Claude, Llama, Mistral, and the Phi model families.<n>Our work establishes a systematic and objective framework for analyzing LLM bias in dialectal queries.
  arXiv  Detail & Related papers  (2024-10-14T18:44:23Z)
• Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom [4.142301960178498]
  SwordsmanImp is the first Chinese multi-turn-dialogue-based dataset aimed at conversational implicature. It includes 200 carefully handcrafted questions, all annotated on which Gricean maxims have been violated. Our results show that GPT-4 attains human-level accuracy (94%) on multiple-choice questions. Other models, including GPT-3.5 and several open-source models, demonstrate a lower accuracy ranging from 20% to 60% on multiple-choice questions.
  arXiv  Detail & Related papers  (2024-04-30T12:43:53Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks [12.665447518524187]
  This study aims to perform a thorough evaluation of the non-English capabilities of SoTA LLMs by comparing them on the same set of multilingual datasets. Our benchmark comprises 22 datasets covering 83 languages, including low-resource African languages. We also perform a study on data contamination and find that several models are likely to be contaminated with multilingual evaluation benchmarks.
  arXiv  Detail & Related papers  (2023-11-13T16:45:37Z)
• Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations [59.056367787688146]
  This paper pioneers exploring and training powerful Multilingual Math Reasoning (xMR) LLMs. We construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages. By utilizing translation, we construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages.
  arXiv  Detail & Related papers  (2023-10-31T08:09:20Z)

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.