# How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models

arXiv: https://arxiv.org/abs/2604.15873 · HTML: https://mlsanity.com/paper/2604.15873/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs](https://mlsanity.com/paper/2501.10970/) (2025)
- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities](https://mlsanity.com/paper/2401.07078/) (2024)
- [M-Prometheus: A Suite of Open Multilingual LLM Judges](https://mlsanity.com/paper/2504.04953/) (2025)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks](https://mlsanity.com/paper/2409.04168/) (2024)
- [Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning](https://mlsanity.com/paper/2402.14856/) (2024)
- [LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High](https://mlsanity.com/paper/2505.22354/) (2025)
- [Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models](https://mlsanity.com/paper/2510.04764/) (2025)
- [Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions](https://mlsanity.com/paper/2506.08952/) (2025)
- [On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts](https://mlsanity.com/paper/2509.06952/) (2025)
- [Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition](https://mlsanity.com/paper/2506.06133/) (2025)
- [They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse](https://mlsanity.com/paper/2506.06775/) (2025)

## Built on by (most cited first, 1 of 1)

- [LLMs Infer Cultural Context but Fail to Apply It When Responding](https://mlsanity.com/paper/2606.17688/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. In this line of work, models are commonly evaluated both as generators of language and as judges of linguistic output, yet these two roles are rarely examined in direct relation to one another. As a result, it remains unclear whether success in one role aligns with success in the other. In this paper, we address this question for pragmatic competence by comparing LLMs' performance as pragmatic listeners, judging the appropriateness of linguistic outputs, and as pragmatic speakers, generating pragmatically appropriate language. We evaluate multiple open-weight and proprietary LLMs across three pragmatic settings. We find a robust asymmetry between pragmatic evaluation and pragmatic generation: many models perform substantially better as listeners than as speakers. Our results suggest that pragmatic judging and pragmatic generation are only weakly aligned in current LLMs, calling for more integrated evaluation practices.