SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models

• URL: http://arxiv.org/abs/2502.14908v2
• Date: Fri, 09 May 2025 18:36:00 GMT
• Title: SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
• Authors: Peter Carragher, Nikitha Rao, Abhinand Jha, R Raghav, Kathleen M. Carley,
• Abstract summary: Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts.<n>This research introduces segsub, a framework for applying targeted image perturbations to investigate VLM resilience against knowledge conflicts.
• Score: 6.52323086990482
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts, impeding their deployment in information-sensitive contexts. While existing research addresses robustness in unimodal models, the multimodal domain lacks systematic investigation of cross-modal knowledge conflicts. This research introduces \segsub, a framework for applying targeted image perturbations to investigate VLM resilience against knowledge conflicts. Our analysis reveals distinct vulnerability patterns: while VLMs are robust to parametric conflicts (20% adherence rates), they exhibit significant weaknesses in identifying counterfactual conditions (<30% accuracy) and resolving source conflicts (<1% accuracy). Correlations between contextual richness and hallucination rate (r = -0.368, p = 0.003) reveal the kinds of images that are likely to cause hallucinations. Through targeted fine-tuning on our benchmark dataset, we demonstrate improvements in VLM knowledge conflict detection, establishing a foundation for developing hallucination-resilient multimodal systems in information-sensitive environments.

Related papers

• When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models [13.390492503308792]
  We analyze the mechanisms that Vision-language models (VLMs) use to resolve cross-modal conflicts.<n>We localize with logit inspection a small set of heads that control the conflict.<n>We show that attention from such heads pinpoints localized image regions driving visual overrides, outperforming gradient-based attribution in precision.
  arXiv  Detail & Related papers  (2025-07-18T12:42:30Z)
• Robust Multimodal Large Language Models Against Modality Conflict [94.12341487880465]
  multimodal large language models (MLLMs) are prone to hallucinations in real-world scenarios.<n>We study the inherent conflicts in inputs from different modalities that place MLLMs in a dilemma and directly lead to hallucinations.<n>Three methods are proposed to alleviate the hallucination caused by modality conflict.
  arXiv  Detail & Related papers  (2025-07-09T11:18:38Z)
• Conflicts in Texts: Data, Implications and Challenges [58.03478157713084]
  Conflicts could reflect the complexity of situations, changes that need to be explained and dealt with, difficulties in data annotation, and mistakes in generated outputs. This survey categorizes these conflicts into three key areas: (1) natural texts on the web, where factual inconsistencies, subjective biases, and multiple perspectives introduce contradictions; (2) human-annotated data, where annotator disagreements, mistakes, and societal biases impact model training; and (3) model interactions, where hallucinations and knowledge conflicts emerge during deployment. We highlight key challenges and future directions for developing conflict-aware NLP systems that can reason over and reconcile conflicting information more effectively
  arXiv  Detail & Related papers  (2025-04-28T04:24:01Z)
• Retrieval-Augmented Generation with Conflicting Evidence [57.66282463340297]
  Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. In practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources. We propose RAMDocs (Retrieval with Ambiguity and Misinformation in Documents), a new dataset that simulates complex and realistic scenarios for conflicting evidence for a user query.
  arXiv  Detail & Related papers  (2025-04-17T16:46:11Z)
• Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models [93.46875303598577]
  Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals remains underexplored.<n>This work investigates how VLMs process ASCII art, a unique medium where textual elements collectively form visual patterns, potentially creating semantic-visual conflicts.
  arXiv  Detail & Related papers  (2025-04-02T10:47:07Z)
• Breaking Focus: Contextual Distraction Curse in Large Language Models [68.4534308805202]
  We investigate a critical vulnerability in Large Language Models (LLMs)<n>This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context.<n>We propose an efficient tree-based search methodology to automatically generate CDV examples.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Analysing the Residual Stream of Language Models Under Knowledge Conflicts [23.96385393039587]
  Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context. This can lead to undesirable model behaviour, such as reliance on outdated or incorrect information.
  arXiv  Detail & Related papers  (2024-10-21T15:12:51Z)
• The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio [118.75449542080746]
  This paper presents the first systematic investigation of hallucinations in large multimodal models (LMMs) Our study reveals two key contributors to hallucinations: overreliance on unimodal priors and spurious inter-modality correlations. Our findings highlight key vulnerabilities, including imbalances in modality integration and biases from training data, underscoring the need for balanced cross-modal learning.
  arXiv  Detail & Related papers  (2024-10-16T17:59:02Z)
• Insight Over Sight? Exploring the Vision-Knowledge Conflicts in Multimodal LLMs [55.74117540987519]
  This paper explores the problem of commonsense-level vision-knowledge conflict in Multimodal Large Language Models (MLLMs) We introduce an automated pipeline, augmented with human-in-the-loop quality control, to establish a benchmark aimed at simulating and assessing the conflicts in MLLMs. We evaluate the conflict-resolution capabilities of nine representative MLLMs across various model families and find a noticeable over-reliance on textual queries.
  arXiv  Detail & Related papers  (2024-10-10T17:31:17Z)
• ECon: On the Detection and Resolution of Evidence Conflicts [56.89209046429291]
  The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems. This study introduces a method for generating diverse, validated evidence conflicts to simulate real-world misinformation scenarios.
  arXiv  Detail & Related papers  (2024-10-05T07:41:17Z)
• Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models [33.76903352835436]
  Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities for capturing and reasoning over multimodal inputs. These models are prone to parametric knowledge conflicts, which arise from inconsistencies of represented knowledge between their vision and language components. We present a systematic approach to detect, interpret, and mitigate them.
  arXiv  Detail & Related papers  (2024-10-04T17:59:28Z)
• AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge [57.66282463340297]
  Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict.
  arXiv  Detail & Related papers  (2024-09-11T16:35:18Z)
• ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM [36.332500824079844]
  Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts has rarely been studied. We present ConflictBank, the first comprehensive benchmark developed to evaluate knowledge conflicts from three aspects. Our investigation delves into four model families and twelve LLM instances, meticulously analyzing conflicts stemming from misinformation, temporal discrepancies, and semantic divergences.
  arXiv  Detail & Related papers  (2024-08-22T02:33:13Z)
• Resolving Knowledge Conflicts in Large Language Models [46.903549751371415]
  Large language models (LLMs) often encounter knowledge conflicts. We ask what are the desiderata for LLMs when a knowledge conflict arises and whether existing LLMs fulfill them. We introduce an evaluation framework for simulating contextual knowledge conflicts.
  arXiv  Detail & Related papers  (2023-10-02T06:57:45Z)
• Trusting Your Evidence: Hallucinate Less with Context-aware Decoding [91.91468712398385]
  Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. We present context-aware decoding (CAD), which follows a contrastive output distribution that amplifies the difference between the probabilities when a model is used with and without context.
  arXiv  Detail & Related papers  (2023-05-24T05:19:15Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)

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.