JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems

arXiv:2604.23478 · cs.CL · Submitted 2026-04-26 · Read on arXiv

cs.CL

Submitted: 2026-04-26

Updated: 2026-09-18

Comments: 35 pages (22 main text, 13 appendix), 3 figures, 14 tables. Judge roster expanded to 25 models across 6 providers; dataset rebuilt (v2.1). Code: https://github.com/rohithreddybc/judgeSense. Dataset: https://huggingface.co/datasets/Rohithreddybc/judgesense-benchmark

Code: https://github.com/rohithreddybc/judgeSense

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Coherence — 75× in this paper · explained in 2 episodes
• Benchmark — 35× in this paper · explained in 2 episodes
• Consistency — 23× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 9× in this paper · explained in 3 episodes
• Position Bias — 7× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 4 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Evaluation Dimensions — 2× in this paper · explained in 3 episodes
• Judge Sensitivity Score — 2× in this paper
• Transactions of the Association for Computational Linguistics — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Agent Harness — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Harness — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 3 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Papers — 1× in this paper · explained in 3 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Gemini: A Family of Highly Capable Multimodal Models
• The Llama 3 Herd of Models
• Mistral 7B
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• Benchmarking Prompt Sensitivity in Large Language Models
• Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
• Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
• Qwen2.5 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering