# Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

arXiv: https://arxiv.org/abs/2603.05485 · HTML: https://mlsanity.com/paper/2603.05485/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking](https://mlsanity.com/paper/2409.15268/) (2024)
- [Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment](https://mlsanity.com/paper/2304.06929/) (2023)
- [Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction](https://mlsanity.com/paper/2509.18658/) (2025)
- [Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations](https://mlsanity.com/paper/2510.11822/) (2025)
- [When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity](https://mlsanity.com/paper/2509.20293/) (2025)
- [Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation](https://mlsanity.com/paper/2512.22245/) (2025)

## Built on by (most cited first, 1 of 1)

- [NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision](https://mlsanity.com/paper/2607.08961/) (2026)

## Abstract (arXiv)

As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-maintaining feedback loops. Any autonomous AI system will depend on automated, verifiable rewards and feedback; in settings where ground truth is sparse or non-deterministic, one practical source of such rewards is an LLM-as-a-Judge. Although LLM judges continue to improve, the literature has yet to introduce systems capable of enforcing standards with strong guarantees, particularly when bias vectors are unknown or adversarially discovered. To remedy this issue, we propose average bias-boundedness (A-BB), an algorithmic framework which formally guarantees reductions of harm/impact as a result of any measurable bias in an LLM judge. Evaluating on Arena-Hard-Auto with four LLM judges, we achieve (tau=0.5, delta=0.01) bias-bounded guarantees while retaining 61-99% correlation with original rankings across formatting and schematic bias settings, with most judge-bias combinations exceeding 80%. The code to reproduce our findings is available at https://github.com/penfever/bias-bounded-evaluation.