# A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

arXiv: https://arxiv.org/abs/2601.21817 · HTML: https://mlsanity.com/paper/2601.21817/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Uncertainty quantification in the Bradley-Terry-Luce model](https://mlsanity.com/paper/2110.03874/) (2021)
- [Uncertainty Quantification of MLE for Entity Ranking with Covariates](https://mlsanity.com/paper/2212.09961/) (2022)
- [Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedback](https://mlsanity.com/paper/2412.19436/) (2024)
- [Ranking Large Language Models without Ground Truth](https://mlsanity.com/paper/2402.14860/) (2024)
- [Covariate Assisted Entity Ranking with Sparse Intrinsic Scores](https://mlsanity.com/paper/2407.08814/) (2024)
- [Uncertainty Quantification for Ranking with Heterogeneous Preferences](https://mlsanity.com/paper/2509.01847/) (2025)
- [Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge](https://mlsanity.com/paper/2505.15240/) (2025)
- [Inference in a generalized Bradley-Terry model for paired comparisons with covariates and a growing number of subjects](https://mlsanity.com/paper/2507.22472/) (2025)

## Built on by (most cited first, 7 of 7)

- [Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges](https://mlsanity.com/paper/2605.09702/) (2026)
- [CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks](https://mlsanity.com/paper/2606.03650/) (2026)
- [Conditional Evaluation of Language Models with Cheap Auxiliary Signals](https://mlsanity.com/paper/2608.16210/) (2026)
- [Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator](https://mlsanity.com/paper/2608.22432/) (2026)
- [Multiple latent orderings better predict language model preferences](https://mlsanity.com/paper/2609.22170/) (2026)
- [OSCAR: Order-aware Sensitivity Correction for AI Rankings](https://mlsanity.com/paper/2609.24128/) (2026)
- [DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration](https://mlsanity.com/paper/2609.31215/) (2026)

## Abstract (arXiv)

Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates. More data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and judge reliability from pairwise comparisons without reference labels. We establish identifiability up to natural normalizations and prove consistency and asymptotic normality of the maximum likelihood estimator, enabling confidence intervals for score differences and rank comparisons. Across multiple public benchmarks and a newly collected dataset, our method improves agreement with human preferences, achieves higher data efficiency than unweighted baselines, and produces calibrated uncertainty quantification for LLM rankings.