Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
This addresses the need for better evaluation methods for role-playing agents in AI applications, though it is incremental as it builds on existing practices.
The paper tackles the problem of evaluating large language models' (LLMs) nuanced understanding of fictional characters by proposing a character profiling task, where LLMs summarize character profiles from materials, and results show promising validation of this capability using the CroSS dataset.
Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequisite for these RPAs lies in the capability of LLMs to understand characters from fictional works. Previous efforts have evaluated this capability via basic classification tasks or characteristic imitation, failing to capture the nuanced character understanding with LLMs. In this paper, we propose evaluating LLMs' character understanding capability via the character profiling task, i.e., summarizing character profiles from corresponding materials, a widely adopted yet understudied practice for RPA development. Specifically, we construct the CroSS dataset from literature experts and assess the generated profiles by comparing them with ground truth references and evaluating their applicability in downstream tasks. Our experiments, which cover various summarization methods and LLMs, have yielded promising results. These results strongly validate the character understanding capability of LLMs. Resources are available at https://github.com/Joanna0123/character_profiling.