Image de couverture de livre

Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feuer, Benjamin, Rosenblatt, Lucas, Elachqar, Oussama
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
par: Feuer, Benjamin, et autres
Publié: (2025)

ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
par: Xu, Bingxin, et autres
Publié: (2025)

MARVIS: Modality Adaptive Reasoning over VISualizations
par: Feuer, Benjamin, et autres
Publié: (2025)

BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
par: Lai, Peng, et autres
Publié: (2026)

Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines
par: Soumik, Sadman Kabir
Publié: (2026)

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
par: Feuer, Benjamin, et autres
Publié: (2024)

Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations
par: Jain, Suryaansh, et autres
Publié: (2025)

Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
par: Shi, Lin, et autres
Publié: (2024)

Large-scale Training of Foundation Models for Wearable Biosignals
par: Abbaspourazad, Salar, et autres
Publié: (2023)

Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL
par: Yang, Yongjin, et autres
Publié: (2024)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
par: Zhang, Hongbin, et autres
Publié: (2026)

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering
par: Zhao, Zixiao, et autres
Publié: (2026)

Quantifying and Mitigating Self-Preference Bias of LLM Judges
par: Yang, Jinming, et autres
Publié: (2026)

Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge
par: Zhou, Xiaolin, et autres
Publié: (2026)

Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge
par: Fujinuma, Yoshinari
Publié: (2025)

Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems
par: Li, Xiaochuan, et autres
Publié: (2025)

Evaluating Metrics for Safety with LLM-as-Judges
par: Clegg, Kester, et autres
Publié: (2025)

Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
par: Ma, Chiyu, et autres
Publié: (2025)

Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
par: Liu, Junhua, et autres
Publié: (2024)

Do LLMs "know" internally when they follow instructions?
par: Heo, Juyeon, et autres
Publié: (2024)

Towards Provably Unlearnable Examples via Bayes Error Optimisation
par: Zhang, Ruihan, et autres
Publié: (2025)

Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model
par: Acikgoz, Emre Can, et autres
Publié: (2025)

JudgeBench: A Benchmark for Evaluating LLM-based Judges
par: Tan, Sijun, et autres
Publié: (2024)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
par: Liu, Yixin, et autres
Publié: (2025)

Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
par: Kumar, Shachi H, et autres
Publié: (2024)

Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge
par: Spiliopoulou, Evangelia, et autres
Publié: (2025)

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation
par: Wang, Yutong, et autres
Publié: (2025)

MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge
par: Lee, Sua, et autres
Publié: (2026)

VERT: Reliable LLM Judges for Radiology Report Evaluation
par: Bologna, Federica, et autres
Publié: (2026)

Knowledge Distillation for LLM-Based Human Activity Recognition in Homes
par: Cumin, Julien, et autres
Publié: (2026)

LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection
par: Hossain, Akram, et autres
Publié: (2026)

Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
par: Dev, Sunishchal, et autres
Publié: (2026)

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
par: Yang, Xianglin, et autres
Publié: (2026)

Provable Coordination for LLM Agents via Message Sequence Charts
par: Bollig, Benedikt, et autres
Publié: (2026)

Provably Bounding Neural Network Preimages
par: Kotha, Suhas, et autres
Publié: (2023)

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
par: Thakur, Aman Singh, et autres
Publié: (2024)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
par: Saha, Swarnadeep, et autres
Publié: (2025)

Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation
par: Huang, Tzu-Heng, et autres
Publié: (2025)

Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory
par: Choi, Junhyuk, et autres
Publié: (2026)

LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems
par: Bonin, Baptiste, et autres
Publié: (2025)