LLMs recover only ~20% of explicit pragmatic shifts under implicit cultural cues across five languages, responding mainly to linguistic structure rather than cultural associations as shown by Hindi-Urdu controls.
A fine-grained comparison of pragmatic language understanding in humans and language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
LLMs perform substantially better as pragmatic listeners judging language than as speakers generating it, revealing weak alignment between the two roles.
citing papers explorer
-
Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation
LLMs recover only ~20% of explicit pragmatic shifts under implicit cultural cues across five languages, responding mainly to linguistic structure rather than cultural associations as shown by Hindi-Urdu controls.
-
How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models
LLMs perform substantially better as pragmatic listeners judging language than as speakers generating it, revealing weak alignment between the two roles.