Evaluating Pragmatic Reasoning in Large Language Models: Evidence from Scalar Diversity
For researchers evaluating pragmatic abilities in LLMs, this work highlights that observed performance is highly dependent on evaluation design, questioning the validity of single-method assessments.
The study investigates whether large language models exhibit stable pragmatic reasoning by comparing direct probability measurement and metalinguistic prompting across models and tasks, finding that pragmatic behavior varies substantially and is not consistently captured by either method.
Evaluating pragmatic reasoning in large language models (LLMs) remains challenging because model behavior can vary depending on evaluation methods. Previous studies suggest that prompt-based judgments may diverge from models' internal probability distributions, raising questions about whether observed performance reflects underlying competence or task-induced behavior. This study examines this issue using scalar diversity as a graded diagnostic for pragmatic inference. Following Hu & Levy (2023), this study compares direct probability measurement and metalinguistic prompting across multiple models and experimental settings. The results show that neither evaluation method consistently outperforms the other and that pragmatic behavior varies substantially across model families, prompting strategies, and task structures. Moreover, scalar diversity gradients emerge only in specific model-condition combinations, suggesting that pragmatic reasoning in LLMs reflects an interaction between internal probabilistic representations and task-induced prompting behavior rather than a stable competence captured by a single evaluation paradigm. These findings highlight the central role of evaluation design in interpreting pragmatic abilities in LLMs.