English
Related papers

Related papers: CyclicJudge: Mitigating Judge Bias Efficiently in …

200 papers

Large language models (LLMs) are increasingly used as automatic evaluators of generative AI outputs, a paradigm often referred to as "LLM-as-a-judge." In practice, LLM judges are imperfect predictions for the underlying truth and can…

Machine Learning · Computer Science 2026-01-12 Yiqun T Chen , Sizhu Lu , Sijia Li , Moran Guo , Shengyi Li

Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexplored. This work is the first study to address a key…

Computation and Language · Computer Science 2025-11-18 Yerin Hwang , Dongryeol Lee , Kyungmin Min , Taegwan Kang , Yong-il Kim , Kyomin Jung

Large Language Models (LLMs) are increasingly used in high-stakes fields where their decisions impact rights and equity. However, LLMs' judicial fairness and implications for social justice remain underexplored. When LLMs act as judges, the…

The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their multilingual evaluation…

Computation and Language · Computer Science 2025-10-31 José Pombal , Dongkeun Yoon , Patrick Fernandes , Ian Wu , Seungone Kim , Ricardo Rei , Graham Neubig , André F. T. Martins

Automatic evaluation using multimodal large language models (MLLMs), commonly referred to as MLLM-as-a-Judge, has been widely used to measure model performance. If such MLLM-as-a-Judge methods were biased, they could distort model…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Shuitsu Koyama , Yuiga Wada , Daichi Yashima , Komei Sugiura

LLM-as-a-Judge has emerged as a popular evaluation strategy, where advanced large language models assess generation results in alignment with human instructions. While these models serve as a promising alternative to human annotators, their…

Computation and Language · Computer Science 2025-05-20 Xiyan Fu , Wei Liu

Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing…

Computers and Society · Computer Science 2025-04-21 Qian Wang , Zhanzhi Lou , Zhenheng Tang , Nuo Chen , Xuandong Zhao , Wenxuan Zhang , Dawn Song , Bingsheng He

Using a language model to score or rank candidate responses has become a scalable alternative to human evaluation in reinforcement learning from human feedback (RLHF) pipelines, benchmarking, and application layer evaluations. However,…

Computation and Language · Computer Science 2026-05-04 Ryan Lail , Luke Markham

Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm…

Artificial Intelligence · Computer Science 2026-01-23 Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Sungryull Sohn , Yunxiang Zhang , Moontae Lee , Hao Peng , Lu Wang , Honglak Lee

With the rapid development of large language models (LLM), the evaluation of LLM becomes increasingly important. Measuring text generation tasks such as summarization and article creation is very difficult. Especially in specific…

Computation and Language · Computer Science 2025-09-25 Kaiqi Zhang , Shuai Yuan , Honghan Zhao

Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM jury composed of three frontier AI models scoring 3333…

LLM-as-judge systems promise scalable, consistent evaluation. We find the opposite: judges are consistent, but not with each other; they are consistent with themselves. Across 3,240 evaluations (9 judges x 120 unique video x pack items x 3…

Artificial Intelligence · Computer Science 2026-01-09 Wajid Nasser

Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, but it remains unclear whether they can reliably assess process faithfulness rather than just answer plausibility. We introduce C2-Faith, a…

Computation and Language · Computer Science 2026-03-06 Avni Mittal , Rauno Arike

Evaluating large language models (LLMs) in diverse and challenging scenarios is essential to align them with human preferences. To mitigate the prohibitive costs associated with human evaluations, utilizing a powerful LLM as a judge has…

Computation and Language · Computer Science 2025-03-10 Tianjun Wei , Wei Wen , Ruizhi Qiao , Xing Sun , Jianghong Ma

Large language models (LLMs) are increasingly integral to information retrieval (IR), powering ranking, evaluation, and AI-assisted content creation. This widespread adoption necessitates a critical examination of potential biases arising…

Information Retrieval · Computer Science 2025-07-11 Krisztian Balog , Donald Metzler , Zhen Qin

Identifying bias in LLM-generated content is a crucial prerequisite for ensuring fairness in LLMs. Existing methods, such as fairness classifiers and LLM-based judges, face limitations related to difficulties in understanding underlying…

Computation and Language · Computer Science 2025-06-11 Zhiting Fan , Ruizhe Chen , Zuozhu Liu

LLM-as-a-Judge leverages the generative and reasoning capabilities of large language models (LLMs) to evaluate LLM responses across diverse scenarios, providing accurate preference signals. This approach plays a vital role in aligning LLMs…

Computation and Language · Computer Science 2025-09-09 Jiachen Yu , Shaoning Sun , Xiaohui Hu , Jiaxu Yan , Kaidong Yu , Xuelong Li

Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the impact of this framing bias on LLM-based evaluation, where…

Computation and Language · Computer Science 2026-01-21 Yerin Hwang , Dongryeol Lee , Taegwan Kang , Minwoo Lee , Kyomin Jung

Evaluating Large Language Models (LLMs) often requires costly human annotations. To address this, LLM-based judges have been proposed, which compare the outputs of two LLMs enabling the ranking of models without human intervention. While…

Computation and Language · Computer Science 2025-05-28 David Salinas , Omar Swelam , Frank Hutter

As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses.…

Artificial Intelligence · Computer Science 2025-03-11 Jiaxin Ai , Pengfei Zhou , Zhaopan Xu , Ming Li , Fanrui Zhang , Zizhen Li , Jianwen Sun , Yukang Feng , Baojin Huang , Zhongyuan Wang , Kaipeng Zhang