AI RESEARCH
TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
arXiv CS.AI
•
ArXi:2605.29656v1 Announce Type: new Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself unexamined. We