作者位次 #6/8ACL 2026Poster· Natural Language Processing
REST : Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
Zhuoshi Pan · Qizhi Pei · Yu Li · Zinan Tang · QiYao Sun · H. Vicky Zhao · Conghui He · Lijun Wu
摘要
Recent Large Reasoning Models (LRMs) have achieved remarkable progress, yet their evaluation still relies on a narrow paradigm: evaluating one question at a time. This single-question setup suffers from two major limitations: (1) vulnerability to data contamination and diminishing difficulty, for...