CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning
📰 ArXiv cs.AI
arXiv:2605.17176v1 Announce Type: new 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 re
Full Article
Title: CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning
Abstract:
arXiv:2605.17176v1 Announce Type: new 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 re
Abstract:
arXiv:2605.17176v1 Announce Type: new 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 re
DeepCamp AI