On the Stability of Prompt Ranking in Large Language Model Evaluation

• URL: http://arxiv.org/abs/2606.24381v1
• Date: Tue, 23 Jun 2026 10:13:47 GMT
• Title: On the Stability of Prompt Ranking in Large Language Model Evaluation
• Abstract summary: This paper systematically studies prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets.<n>We find that while overall rank correlations are often moderate to high, the identity of the top-performing prompt frequently changes, leading to unreliable selection decisions.<n>We propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance.
• Score: 9.718200364661675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the identity of the top-performing prompt frequently changes, leading to unreliable selection decisions. To address this issue, we propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance. Our results show that this approach improves robustness in unstable settings while remaining competitive in more stable regimes. These findings highlight the importance of accounting for evaluation uncertainty in prompt selection and LLM benchmarking.

Related papers

• Boosting Self-Consistency with Ranking [56.38798757709555]
  Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer.<n>We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem.
  arXiv  Detail & Related papers  (2026-06-03T16:12:30Z)
• Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking [0.4562811934651716]
  We formulate checkpoint selection as a robust decision problem under evaluation uncertainty.<n>We propose a multi-stage framework that integrates curated real-world data, structured LLM-based judgment, and multi-stage ranking protocols.<n>We demonstrate that data quality, specifically OCR readability, is a critical determinant of evaluation validity.
  arXiv  Detail & Related papers  (2026-05-13T12:18:32Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems [3.263813419432528]
  Majority vote discards annotator reliability and item-level ambiguity, often yielding unstable comparisons.<n>We introduce STABLEVAL, a disagreement-aware evaluation framework.<n>STABLEVAL is explicitly designed for stable and uncertainty-aware system evaluation.
  arXiv  Detail & Related papers  (2026-05-04T01:03:48Z)
• Permutation-Consensus Listwise Judging for Robust Factuality Evaluation [0.8563354084119061]
  We study candidate-order sensitivity in listwise factuality evaluation.<n>We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set.<n>On RewardBench 2 Factuality, PCFJudge improves over direct judging by up to 7 absolute points.
  arXiv  Detail & Related papers  (2026-03-20T23:35:14Z)
• RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty [102.02839046225468]
  RankLLM is a novel framework designed to quantify both question difficulty and model competency.<n>We evaluate 30 models on 35,550 questions across multiple domains.
  arXiv  Detail & Related papers  (2026-02-12T21:28:46Z)
• Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification [9.99813918008511]
  We study prompt-dependent ranking inference under pairwise human preferences.<n>We develop a framework for decision-safe rankings with statistically valid uncertainty guarantees.
  arXiv  Detail & Related papers  (2026-02-11T18:16:24Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• In-context Ranking Preference Optimization [65.5489745857577]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• Measuring the Inconsistency of Large Language Models in Preferential Ranking [6.723531714964794]
  This study investigates the capacity of large language models to provide consistent ordinal preferences. We introduce a formalization of consistency based on order theory, outlining criteria such as transitivity, asymmetry, reversibility, and independence from irrelevant alternatives. Our diagnostic experiments on selected state-of-the-art LLMs reveal their inability to meet these criteria, indicating a strong positional bias and poor transitivity.
  arXiv  Detail & Related papers  (2024-10-11T14:27:18Z)

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.