作者位次 #5/5NeurIPS 2026Poster· Social Aspects / Accountability, Transparency and Interpretability
Peer review should constrain evaluative authority
Hanrui Wang · Timo Spinde · Isabella Habereder · Chun-Shien Lu · Isao Echizen
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Hanrui Wang · Timo Spinde · Isabella Habereder · Chun-Shien Lu · Isao Echizen
Xin Sun · Di Wu · Sijing Qin · Isao Echizen · Abdallah El Ali · Saku Sugawara
Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher tru...