CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning

TL;DR

CAREBench is a novel benchmark designed to evaluate LLMs' emotion understanding by analyzing their ability to perform appraisal reasoning and capture the cognitive processes behind emotion generation.

Contribution

It introduces a comprehensive evaluation framework with complete inferential chain annotations based on appraisal theory, filling a gap in emotion understanding assessment.

Findings

Stronger models match or surpass humans on some tasks.

Models struggle with appraisal reasoning and positive emotion recognition.

Performance varies across chain steps and is affected by appraisal interventions.

Abstract

Emotion understanding is a core capability for LLMs to interact effectively with humans, yet existing evaluation paradigms rely on discrete emotion label prediction and fail to capture the cognitive processes underlying emotion generation. Grounded in appraisal theory, we introduce CAREBench, the first benchmark with complete inferential chain annotations from both first- and third-person perspectives on real-world narratives, spanning appraisal reasoning, appraisal ratings, and multi-label emotion annotation. We propose a process-level evaluation framework and conduct systematic experiments across six LLMs organized around four research questions. We find that stronger models match or surpass human observers on certain tasks, yet fall short on appraisal reasoning and positive emotion recognition; performance across chain steps and sensitivity to appraisal interventions exhibit dissociations across models; and current models have not internalized the mechanisms needed to capture human subjective heterogeneity. These findings suggest that downstream emotion prediction metrics may overestimate LLMs' true emotion understanding, and CAREBench provides a foundation for more diagnostically informative evaluation of LLMs' affective cognitive capabilities.