Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

• URL: http://arxiv.org/abs/2605.18852v1
• Date: Wed, 13 May 2026 12:18:32 GMT
• Title: Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
• Abstract summary: 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.
• Score: 0.4562811934651716
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and evaluation signals are prone to noise. Existing methodologies rely heavily on static benchmarks or pointwise scoring, which frequently misalign with in-the-wild usage and lack robust uncertainty estimation, particularly in OCR-heavy scenarios. In this work, we formulate checkpoint selection as a robust decision problem under evaluation uncertainty. We propose a multi-stage framework that integrates curated real-world data, structured LLM-based judgment, and multi-stage ranking protocols. The evaluation system orchestrates progressive refinement via pointwise filtering, listwise ranking, and pairwise comparison. To enhance reliability, we introduce subsampling-based confidence estimation and a percentile-based scoring formulation that captures distributional characteristics while penalizing tail failures. Furthermore, we demonstrate that data quality, specifically OCR readability, is a critical determinant of evaluation validity.

Related papers

• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• On the Stability of Prompt Ranking in Large Language Model Evaluation [9.718200364661675]
  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.
  arXiv  Detail & Related papers  (2026-06-23T10:13:47Z)
• Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate [2.1987782243719898]
  We investigate whether intrinsic confidence signals, token-level log-probabilities from decoding, can predict reasoning quality.<n>We find that early-token confidence, particularly within the first few generated tokens, is consistently the strongest predictor of reasoning quality.
  arXiv  Detail & Related papers  (2026-06-09T01:52:59Z)
• 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)
• LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy [1.3254304182988286]
  We propose Adaptive Conformal Semantic Entropy (ACSE), a method for estimating prompt-level uncertainty.<n>Our uncertainty scoring function is based on clustering semantic entropy of multiple diverse responses to the same prompt.<n>Our approach consistently outperforms state-of-the-art uncertainty quantification baselines.
  arXiv  Detail & Related papers  (2026-05-05T20:56:11Z)
• 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)
• ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning [2.1461777157838724]
  We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in large language models (LLMs) reasoning.<n>Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability.<n>We further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability.
  arXiv  Detail & Related papers  (2025-12-08T18:26:58Z)
• 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)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection [56.302586730134806]
  We introduce Confidence-Consistency Evaluation (CCE), a novel evaluation metric.<n>CCE simultaneously measures prediction confidence and uncertainty consistency.<n>We also establish RankEval, a benchmark for comparing the ranking capabilities of various metrics.
  arXiv  Detail & Related papers  (2025-09-01T03:38:38Z)
• MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels [16.300463494913593]
  Large Language Models (LLMs) require robust confidence estimation.<n>McQCA-Eval is an evaluation framework for assessing confidence measures in Natural Language Generation.
  arXiv  Detail & Related papers  (2025-02-20T05:09:29Z)
• Beyond the Singular: The Essential Role of Multiple Generations in Effective Benchmark Evaluation and Analysis [10.133537818749291]
  Large language models (LLMs) have demonstrated significant utilities in real-world applications.<n> Benchmark evaluations are crucial for assessing the capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-02-13T03:43:33Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)

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.