Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective Evaluation

arXiv:2608.30373 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Alignment — 34× in this paper · explained in 1 episode
• Ablation — 10× in this paper · explained in 1 episode
• Consistency — 9× in this paper · explained in 3 episodes
• LLM judge — 6× in this paper · explained in 2 episodes
• Multi-Agent Debate — 6× in this paper
• Aggregation — 4× in this paper · explained in 1 episode
• Agent-as-Judge — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes

Sources

• Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
• Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
• SummEval: Re-evaluating Summarization Evaluation
• Gemma 3 Technical Report
• Self-Preference Bias in LLM-as-a-Judge

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