作者位次 #2/5ACL 2026Findings· Findings of ACL
B loom E val: A Bloom’s Cognitive Taxonomy-Based Benchmark for Evaluating LRM s via Cognitive Hierarchy Trace
Zhiyi Duan · Lei Gao · Jiangshan Guan · Qi Wang · Rui Liu
摘要
Current benchmarks for Large Reasoning Models (LRMs) primarily rely on answer correctness, failing to assess the structural coherence and cognitive soundness of the reasoning process itself. To address this gap, we introduce Cognitive Hierarchy Trace (CHT), a novel evaluation framework grounded i...