VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages

2026-09-01

AI Summary

本文通过建立VakyArth基准来评估印地语系语言中大型语言模型的语用能力，使用多选题、自然语言推理和翻译等方法揭示了这些模型在理解和处理特定文化背景下的隐含意义时存在的问题。

Abstract

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.

Problem

• Pragmatic Competence
• Indic Languages
• LLMs
• Cultural Conventions
• Linguistic Diversity

Innovation

• pragmatic benchmark
• Indic languages
• multilingual LLMs
• diagnostic evaluation
• cultural conventions