Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification

• URL: http://arxiv.org/abs/2512.16921v1
• Date: Thu, 18 Dec 2025 18:59:57 GMT
• Title: Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
• Authors: Qihao Liu, Chengzhi Mao, Yaojie Liu, Alan Yuille, Wen-Sheng Chu,
• Abstract summary: AuditDM is an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence.<n>Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.
• Score: 30.86763472476859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence. AuditDM fine-tunes an MLLM as an auditor via reinforcement learning to generate challenging questions and counterfactual images that maximize disagreement among target models. Once trained, the auditor uncovers diverse, interpretable exemplars that reveal model weaknesses and serve as annotation-free data for rectification. When applied to SoTA models like Gemma-3 and PaliGemma-2, AuditDM discovers more than 20 distinct failure types. Fine-tuning on these discoveries consistently improves all models across 16 benchmarks, and enables a 3B model to surpass its 28B counterpart. Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.

Related papers

• ProbeLLM: Automating Principled Diagnosis of LLM Failures [89.44131968886184]
  We propose ProbeLLM, a benchmark-agnostic automated probing framework that elevates weakness discovery from individual failures to structured failure modes.<n>By restricting probing to verifiable test cases and leveraging tool-augmented generation and verification, ProbeLLM grounds failure discovery in reliable evidence.
  arXiv  Detail & Related papers  (2026-02-13T14:33:13Z)
• M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data [9.502531621979694]
  We introduce Merging-ensembling loss (M-Loss), a novel evaluation metric.<n>M-Loss quantifies the compatibility of merging source models using very limited unlabeled data.<n>Our theoretical analysis and empirical evaluations demonstrate that incorporating M-Loss into the merging process significantly improves the alignment between merged models and model ensembling.
  arXiv  Detail & Related papers  (2026-02-09T12:03:36Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning [22.39245479538899]
  We introduce modality sabotage, a diagnostic failure mode in which a high-confidence unimodal error overrides other evidence and misleads the fused result.<n>A model-agnostic evaluation layer treats each modality as an agent, producing candidate labels and a brief self-assessment used for auditing.<n>A simple fusion mechanism aggregates these outputs, exposing contributors (modalities supporting correct outcomes) and saboteurs (modalities that mislead)
  arXiv  Detail & Related papers  (2025-11-04T18:20:13Z)
• A Perplexity and Menger Curvature-Based Approach for Similarity Evaluation of Large Language Models [0.6906005491572401]
  Large Language Models (LLMs) have brought concerns regarding copyright infringement and unethical practices in data and model usage.<n>This paper introduces a novel metric for quantifying LLM similarity, which leverages perplexity curves and differences in Menger curvature.
  arXiv  Detail & Related papers  (2025-04-05T16:04:25Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs [32.45604456988931]
  This study establishes baseline comparisons for Automated Fact-Checking (AFC) using Large Language Models (LLMs)<n>We evaluate Llama-3 models of varying sizes on 17,856 claims collected from PolitiFact (2007-2024) using evidence retrieved via restricted web searches.<n>Our results show that larger LLMs consistently outperform smaller LLMs in classification accuracy and justification quality without fine-tuning.
  arXiv  Detail & Related papers  (2025-02-13T02:51:17Z)
• Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework [79.40678802098026]
  Math Word Problems serve as a crucial benchmark for evaluating Large Language Models' reasoning abilities.<n>Current error classification methods rely on static and predefined categories.<n>We propose Error-Aware Prompting (EAP) that incorporates common error patterns as explicit guidance.
  arXiv  Detail & Related papers  (2025-01-26T16:17:57Z)
• Ranked from Within: Ranking Large Multimodal Models Without Labels [73.96543593298426]
  We show that uncertainty scores derived from softmax distributions provide a robust basis for ranking models across various tasks.<n>This facilitates the ranking of LMMs on unlabeled data, providing a practical approach for selecting models for diverse target domains without requiring manual annotation.
  arXiv  Detail & Related papers  (2024-12-09T13:05:43Z)
• DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation [18.77296551727931]
  We propose DECIDER, a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image models. DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-08-01T07:08:11Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)

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.