Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation

arXiv:2608.05726 · cs.CL, cs.AI · Submitted 2026-08-06 · Read on arXiv

Yuma Asato, Kiyoaki Shirai, Natthawut Kertkeidkachorn

cs.CL, cs.AI

Submitted: 2026-08-06

Updated: 2026-08-10

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

Terminology

• LLM-as-a-Judge — 16× in this paper · explained in 4 episodes
• Calibration — 14× in this paper · explained in 9 episodes
• Coherence — 6× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Semantic Textual Relatedness — 4× in this paper
• Distribution Calibration — 3× in this paper
• Language Models (LLMs) — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 9 episodes
• Perplexity — 3× in this paper · explained in 3 episodes
• Contextual Calibration — 2× in this paper
• Semantic Textual Similarity — 2× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 8 episodes
• Generator — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 7 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Position Bias — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Score Distribution Divergence — 1× in this paper

Sources

• GPT-4 Technical Report
• Deterministic or probabilistic? The psychology of LLMs as random number generators
• Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge
• The Illusion of Stochasticity in LLMs
• Exploring the Effects of Alignment on Numerical Bias in Large Language Models
• Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions

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