一作ACL 2026Findings· Findings of ACL
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
Shuliang Liu · Zhipeng Xu · Zhenghao Liu · Yukun Yan · Minghe Yu · Yu Gu · an Jiaotong University) · Huiyuan Xie · Ge Yu
摘要
Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibi...