The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively understudied; existing work mainly pursued optimal performance in terms of correlating LLM scores with human expert scores. In this paper, we conduct a series of analyses using the SummEval dataset and confirm that LLMs are biased evaluators as they: (1) exhibit familiarity bias-a preference for text with lower perplexity, (2) show skewed and biased distributions of ratings, and (3) experience anchoring effects for multi-attribute judgments. We also found that LLMs are inconsistent evaluators, showing low "inter-sample" agreement and sensitivity to prompt differences that are insignificant to human understanding of text quality. Furthermore, we share recipes for configuring LLM evaluators to mitigate these limitations. Experimental results on the RoSE dataset demonstrate improvements over the state-of-the-art LLM evaluators.
Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
Northeastern University（东北大学）；Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning (MCML), LMU Munich（慕尼黑大学慕尼黑机器学习中心）
Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks
East China Normal University（华东师范大学）；Shanghai Institute of Artificial Intelligence for Education（上海人工智能教育研究院）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Yangzhou University（扬州大学）；School of Education and Intelligent Education Research Center, Yangzhou University（扬州大学教育学院与智能教育研究中心）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）
MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models
Yonsei University（延世大学）；KAIST（韩国科学技术院）；OneLineAI；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Artful Media；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Carnegie Mellon University（卡内基梅隆大学）
Latent space bias directions in LLMs capture confidence, not fairness
Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge（剑桥大学天文学研究所及卡夫利宇宙学研究所）；Risk and Security AI Lab, Visa Inc.（Visa公司风险与安全人工智能实验室）
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
National Institute of Informatics (NII)（国立信息学研究所）；University of Amsterdam（阿姆斯特丹大学）；University of Tokyo（东京大学）；Hitotsubashi University（一桥大学）；Centrum Wiskunde & Informatica (CWI)（荷兰数学与计算机科学研究中心）；Utrecht University（乌得勒支大学）
