Does It Fail to See or Fail to Know? Attributing Errors in Vision-Language Models

• URL: http://arxiv.org/abs/2607.04683v2
• Date: Fri, 10 Jul 2026 10:34:34 GMT
• Title: Does It Fail to See or Fail to Know? Attributing Errors in Vision-Language Models
• Abstract summary: Uncertainty should not only indicate whether the model is likely to fail but also diagnose why it is uncertain.<n>We propose a unified framework for disentangling failure modes and investigate whether pre-generation signals can predict these failure sources.<n>Our main finding is that recognition-related failures are best captured by visual-token representations, while failures that remain after recognition are better captured by prompt-conditioned hidden states.
• Score: 33.564453692157095
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) perform well on visual question answering with high-quality images but struggle when questions require knowledge beyond what is clearly and directly visible. In such settings, uncertainty quantification should not only indicate whether the model is likely to fail but also diagnose why it is uncertain, across dimensions such as perception, entity recognition, and knowledge retrieval. While prior work has focused on individual failure modes in isolation or treated incorrect answers as monolithic failures, we propose a unified framework for disentangling these failure modes and investigate whether pre-generation signals can predict these failure sources. Across a range of datasets and model families, we find a consistent pattern in VLM errors: some failures arise from visual or recognition bottlenecks, while others persist after the relevant entity is identified. Our main finding is that these failure sources can be predicted before decoding: recognition-related failures are best captured by visual-token representations, while failures that remain after recognition are better captured by prompt-conditioned hidden states. This pre-generation signal enables efficient failure-source prediction before the model produces an answer, allowing uncertain cases to be routed to targeted interventions such as image repair, entity recognition support, or external retrieval.

Related papers

• MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts [10.608824155356377]
  We present MissingBench-Verified, a benchmark designed to evaluate a specific and practically relevant scenario.<n>We observe consistent and significant failure rates that persist even when external tool evidence explicitly contradicts the model's visual perception.<n>We find that existing mitigation strategies, including tool-assisted verification, autonomous visual reasoning, longer reasoning durations, and fine-tuning on an easier dataset, provide negligible improvement.
  arXiv  Detail & Related papers  (2026-07-21T03:43:50Z)
• Can Large Language Models Generate Observability-Aware Code? [51.30941152293301]
  We present a systematic study of observability in agent-generated systems.<n>Our results reveal a consistent gap between diagnostic semantics at the source level and fault signals at runtime.<n>We introduce an observability-oriented skill, which can serve as a guidance to improve both diagnostic semantics and fault-signal exposure.
  arXiv  Detail & Related papers  (2026-07-07T03:20:52Z)
• How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures [21.666726162280696]
  Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace.<n>The first is committed failure, in which a model locks onto an incorrect reasoning path early in its trace.<n>In the second, persistent uncertainty instead accumulates throughout, and the full trace is needed to best distinguish failing from successful completions.
  arXiv  Detail & Related papers  (2026-06-04T18:36:42Z)
• Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)? [72.2500547961037]
  spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments.<n>We introduce two types of observation challenges: (1) occlusion, which hides target information, and (2) perspective ambiguity, which produces misleading visual cues.<n>For each configuration, we design spatial questions that are answerable under clean observations but require abstention under the introduced challenges.
  arXiv  Detail & Related papers  (2026-05-28T20:44:47Z)
• Unveiling the Visual Counting Bottleneck in Vision-Language Models [49.591496870141846]
  This work deconstructs visual counting into three cognitive stages: visual individuation, magnitude awareness, and symbolic mapping.<n>Using synthetic Go boards and linear probes, we demonstrate that visual backbones maintain robust, linearly separable representations of quantity well into the extrapolation regime.<n>We pinpoint the collapse to the symbolic mapping stage, where the model fails to project valid visual magnitudes onto symbolic tokens.
  arXiv  Detail & Related papers  (2026-05-28T16:20:29Z)
• FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition [54.31138496553705]
  Fine-grained recognition in everyday life is often not a closed-book classification problem.<n>Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored.<n>We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions.
  arXiv  Detail & Related papers  (2026-05-13T08:49:51Z)
• The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation [18.83395586542378]
  Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG)<n>We identify and formalize the phenomenon of recorruption, where the introduction of even perfectly accurate "oracle" context causes a capable model to abandon an initially correct prediction.<n>We propose Bottleneck Attention Intervention for Recovery (BAIR), a parameter-free, inference-time framework that restores visual saliency and applies position-aware penalties to textual distractors.
  arXiv  Detail & Related papers  (2026-05-07T02:27:04Z)
• Are vision language models robust to uncertain inputs? [5.249651874118556]
  We show that newer and larger vision language models exhibit improved robustness compared to earlier models, but still suffer from a tendency to strictly follow instructions.<n>For natural images such as ImageNet, this limitation can be overcome without pipeline modifications.<n>We propose a novel mechanism based on caption diversity to reveal a model's internal uncertainty.
  arXiv  Detail & Related papers  (2025-05-17T03:16:49Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset [7.1083241462091165]
  Traditional defect classification approaches are facing with two barriers. Insufficient training data and unstable data quality. We propose the special dataset, including rich data description recorded on image, for defect classification, but the defect feature is uneasy to learn directly.
  arXiv  Detail & Related papers  (2024-04-08T04:17:27Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging [12.732665048388041]
  Machine learning models commonly exhibit unexpected failures post-deployment. We aim to standardise and bring principles to this process through answering two critical questions. We suggest that the quality of the identified failure types can be validated through measuring the intra- and inter-type generalisation. We argue that a model can be considered repaired if it achieves high accuracy on the failure types while retaining performance on the previously correct data.
  arXiv  Detail & Related papers  (2021-09-25T12:04:19Z)

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.