CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models

• URL: http://arxiv.org/abs/2607.28991v1
• Date: Fri, 31 Jul 2026 03:38:12 GMT
• Title: CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models
• Abstract summary: We propose CAER, a backbone-agnostic framework for visual-language conflict detection and conflict-aware generation.<n>We show that CAER effectively detects visual-language conflicts and improves the reliability of open-source MLLMs without updating their backbone parameters.
• Score: 25.759863166571858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inputs conflict with visual evidence, they still suffer from hallucinations and produce responses inconsistent with visual content. Existing approaches mainly rely on decoding strategies, additional training, verification methods, or prompting techniques, but often lack fine-grained conflict localization and conflict-aware generation. In this work, we propose CAER, a backbone-agnostic framework for visual-language conflict detection and conflict-aware generation. CAER introduces a span-grounded evidence router that transforms claim representations into soft textual queries and retrieves corresponding evidence from frozen visual tokens, enabling fine-grained conflict estimation. Furthermore, we design a dual-prefix expert routing mechanism that learns separate experts for visually supported and contradicted inputs, enabling conflict-aware generation through explicit expert selection. Experiments on the public MMMC benchmark and our newly curated AgriConflict dataset demonstrate that CAER effectively detects visual-language conflicts and improves the reliability of open-source MLLMs without updating their backbone parameters.

Related papers

• CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection [56.64398465636452]
  generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability.<n>We propose textbfConflict-textbfOriented textbfREasoning (textbfCORE) framework, an effective paradigm that learns to endows multimodal large language models (MLLMs) with explicit conflict-capturing capability.<n> CORE achieves robust and generalizable conflict detection, effectively and rapidly adapting to unseen manipulation types with a few samples or in even zero-shot settings.
  arXiv  Detail & Related papers  (2026-06-02T02:53:48Z)
• Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding [51.242997961841276]
  Large language models accumulate parametric knowledge through pre-training.<n> knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context.<n>Existing methods address knowledge conflicts through contrastive decoding, but in conflict-free scenarios, static approaches disrupt output distribution.<n>We propose Dynamic Cognitive Reconciliation Decoding (DCRD), to predict and context-memory conflicts.
  arXiv  Detail & Related papers  (2026-05-12T14:29:45Z)
• Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning [78.86309644343295]
  Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals.<n>We formalize these failures under a unified notion of knowledge conflict, distinguishing input-level objective conflict from process-level effective conflict.<n>Our findings provide a mechanism-level view of multimodal reasoning under knowledge conflict and enable principled diagnosis and control of long-CoT failures.
  arXiv  Detail & Related papers  (2026-02-16T07:10:44Z)
• Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs [17.56537230934894]
  Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks.<n>We show that these models are indeed vulnerable to misleading textual prompts, often overriding clear visual evidence in favor of the conflicting text.
  arXiv  Detail & Related papers  (2026-01-27T05:04:38Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation [7.927396904317054]
  Knowledge conflict often arises in RAG systems, where retrieved documents may be inconsistent with one another or contradict the model's parametric knowledge.<n>We propose a knowledge graph (KG)-based framework that generates varied and subtle conflicts between two similar yet distinct contexts.<n> Experimental results on our benchmark, MAGIC, provide intriguing insights into the inner workings of LLMs regarding knowledge conflict.
  arXiv  Detail & Related papers  (2025-07-29T07:19:49Z)
• 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)
• SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models [6.52323086990482]
  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.
  arXiv  Detail & Related papers  (2025-02-19T00:26:38Z)
• 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)

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.