作者位次 #2/11ACL 2026Findings· Findings of ACL
Scaling Evaluation-Time Compute with Reasoning Models as Evaluators
Seungone Kim · Ian Wu · Jinu Lee · Xiang Yue · Seongyun Lee · Minkyeong Moon · Carolin Lawrence · Kiril Gashteovski · Julia Hockenmaier · Graham Neubig · Sean Welleck
摘要
Language model (LM) evaluators that generate chain-of-thought (CoT) reasoning are widely used for the assessment of LM responses. Simultaneously, increasing LMs’ “thinking” time through scaling test-time compute has proven to be an effective technique for solving challenging problems in domains s...