# VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages

arXiv: https://arxiv.org/abs/2609.01788 · HTML: https://mlsanity.com/paper/2609.01788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition](https://mlsanity.com/paper/2004.03066/) (2020)
- [PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities](https://mlsanity.com/paper/2401.07078/) (2024)
- [The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://mlsanity.com/paper/2210.14986/) (2022)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data](https://mlsanity.com/paper/2406.15053/) (2024)
- [Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset](https://mlsanity.com/paper/2007.01176/) (2020)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization](https://mlsanity.com/paper/2401.14280/) (2024)
- [On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena](https://mlsanity.com/paper/2501.04662/) (2025)
- [Modeling Cross-Cultural Pragmatic Inference with Codenames Duet](https://mlsanity.com/paper/2306.02475/) (2023)
- [Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models](https://mlsanity.com/paper/2105.03495/) (2021)
- [Pragmatic Competence Evaluation of Large Language Models for the Korean Language](https://mlsanity.com/paper/2403.12675/) (2024)
- [Evaluating Large language models on Understanding Korean indirect Speech acts](https://mlsanity.com/paper/2502.10995/) (2025)
- [The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models](https://mlsanity.com/paper/2505.18497/) (2025)

## Abstract (arXiv)

Real-world communication often requires pragmatic reasoning: interpreting meanings implied through context and cultural convention rather than stated literally. Existing pragmatic evaluation remains largely limited to English and high-resource languages, leaving Indic languages unexplored despite their linguistic and cultural diversity. We introduce VakyArth, the first pragmatic benchmark for Indic languages, designed as a diagnostic evaluation covering Hindi, Punjabi, Tamil, and Malayalam. VakyArth evaluates models across five phenomena: deixis, speech acts, implicature, social pragmatics, and coherence; through multiple-choice questions, natural language inference, and translation, with all items authored by native speakers. Across multilingual large language models (LLMs) of varying families and sizes, we find consistent failures on pragmatic meanings rooted in Indic linguistic and cultural conventions. Our analysis shows systematic differences across languages and tasks: MCQ accuracy exceeds NLI accuracy in all model-language combinations, translation performance does not reliably track pragmatic understanding, and Indo-Aryan languages show a translation advantage over Dravidian languages. We further show that automatic translation metrics can miss fluent but pragmatically unfaithful outputs, especially for implicature and deixis.