am-ELO: A Stable Framework for Arena-based LLM Evaluation

• URL: http://arxiv.org/abs/2505.03475v2
• Date: Thu, 29 May 2025 08:23:44 GMT
• Title: am-ELO: A Stable Framework for Arena-based LLM Evaluation
• Authors: Zirui Liu, Jiatong Li, Yan Zhuang, Qi Liu, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang,
• Abstract summary: Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators.<n>We introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System.
• Score: 28.54576582498528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the consistency and stability of the MLE approach for model ranking. Additionally, we proposed the am-ELO, which modify the Elo Rating's probability function to incorporate annotator abilities, enabling the simultaneous estimation of model scores and annotator reliability. Experiments demonstrate that this method ensures stability, proving that this framework offers a more robust, accurate, and stable evaluation method for LLMs.

Related papers

• LLMEval-3: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models [51.55869466207234]
  Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting.<n>We introduce LLMEval-3, a framework for dynamic evaluation of LLMs.<n>LLEval-3 is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run.
  arXiv  Detail & Related papers  (2025-08-07T14:46:30Z)
• Beyond Single-Point Judgment: Distribution Alignment for LLM-as-a-Judge [24.862965044243168]
  Previous methods rely on single-point evaluations, overlooking the inherent diversity and uncertainty in human evaluations.<n>We propose a novel training framework that explicitly aligns the LLM-generated judgment distribution with empirical human distributions.<n>Our framework significantly outperforms existing closed-source LLMs and conventional single-point alignment methods.
  arXiv  Detail & Related papers  (2025-05-18T08:33:09Z)
• Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment [63.07424521895492]
  Model Inversion (MI) attacks aim to reconstruct information from private training data by exploiting access to machine learning models T.<n>The standard evaluation framework for such attacks relies on an evaluation model E, trained under the same task design as T.<n>This framework has become the de facto standard for assessing progress in MI research, used across nearly all recent MI attacks and defenses without question.
  arXiv  Detail & Related papers  (2025-05-06T13:32:12Z)
• Revisiting LLM Evaluation through Mechanism Interpretability: a New Metric and Model Utility Law [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>We propose a novel metric, the Model Utilization Index (MUI), which introduces mechanism interpretability techniques to complement traditional performance metrics.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• Re-evaluating Open-ended Evaluation of Large Language Models [50.23008729038318]
  We show that the current Elo-based rating systems can be susceptible to and even reinforce biases in data, intentional or accidental.<n>We propose evaluation as a 3-player game, and introduce novel game-theoretic solution concepts to ensure robustness to redundancy.
  arXiv  Detail & Related papers  (2025-02-27T15:07:47Z)
• An Empirical Analysis of Uncertainty in Large Language Model Evaluations [28.297464655099034]
  We conduct experiments involving 9 widely used LLM evaluators across 2 different evaluation settings.<n>We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes.<n>We find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent.
  arXiv  Detail & Related papers  (2025-02-15T07:45:20Z)
• Self-Evolving Critique Abilities in Large Language Models [59.861013614500024]
  This paper explores enhancing critique abilities of Large Language Models (LLMs)<n>We introduce SCRIT, a framework that trains LLMs with self-generated data to evolve their critique abilities.<n>Our analysis reveals that SCRIT's performance scales positively with data and model size.
  arXiv  Detail & Related papers  (2025-01-10T05:51:52Z)
• Reward-Robust RLHF in LLMs [25.31456438114974]
  Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence. The reliance on reward-model-based (RM-based) alignment methods introduces significant challenges. We introduce a reward-robust RLHF framework aimed at addressing these fundamental challenges.
  arXiv  Detail & Related papers  (2024-09-18T02:35:41Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models [36.273451767886726]
  FreeEval is a modular and scalable framework crafted to enable trustworthy and efficient automatic evaluations of large language models. FreeEval's unified abstractions simplify the integration and improve the transparency of diverse evaluation methodologies. The framework integrates meta-evaluation techniques like human evaluation and data contamination detection, which, along with dynamic evaluation modules, enhance the fairness of the evaluation outcomes.
  arXiv  Detail & Related papers  (2024-04-09T04:17:51Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• Elo Uncovered: Robustness and Best Practices in Language Model Evaluation [9.452326973655447]
  We study two axioms that evaluation methods should adhere to: reliability and transitivity. We show that these axioms are not always satisfied raising questions about the reliability of current comparative evaluations of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T00:45:23Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.