PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?

Lingfeng Zhou, Jialing Zhang, Jin Gao, Mohan Jiang, Dequan Wang

Keywords: Role-play, evaluating LLM evaluators, benchmark

TL;DR: We introduce PersonaEval, a benchmark showing that LLMs struggle to judge role-play like humans. Even top models fail basic role identification, highlighting a need for more human-like reasoning in LLM evaluators.

Abstract: Current role-play studies often rely on unvalidated LLM-as-a-judge paradigms, which may fail to reflect how humans perceive role fidelity. A key prerequisite for human-aligned evaluation is role identification, the ability to recognize who is speaking based on dialogue context. We argue that any meaningful judgment of role-playing quality (how well a character is played) fundamentally depends on first correctly attributing words and actions to the correct persona (who is speaking). We present PersonaEval, the first benchmark designed to test whether LLM evaluators can reliably identify human roles. PersonaEval uses human-authored dialogues from novels, scripts, and video transcripts, challenging models to determine the correct persona according to the conversation context. Our experiments, including a human study, show that even the best-performing LLMs reach only around 69% accuracy, well below the level needed for reliable evaluation. In contrast, human participants perform near ceiling with 90.8% accuracy, highlighting that current LLM evaluators are still not human enough to effectively judge role-play scenarios. To better understand this gap, we examine training-time adaptation and test-time compute, suggesting that reliable evaluation requires more than task-specific tuning, but depends on strong, human-like reasoning abilities in LLM evaluators. We release our benchmark at https://github.com/maple-zhou/PersonaEval.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 652