mlsanityData to 14 Oct 2026

Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models

arXiv 2505.19509 ↗First posted 26 May 2025cs.LG cs.AIcited by 19

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

also in 1 more
Abstract (arXiv)

Large Multimodal Models(LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation(RAG) frameworks where the contextual information from external sources may contradict the model's internal parametric knowledge, leading to unreliable outputs. However, existing benchmarks fail to reflect such realistic conflict scenarios. Most focus solely on intra-memory conflicts, while context-memory and inter-context conflicts remain largely investigated. Furthermore, commonly used factual knowledge-based evaluations are often overlooked, and existing datasets lack a thorough investigation into conflict detection capabilities. To bridge this gap, we propose MMKC-Bench, a benchmark designed to evaluate factual knowledge conflicts in both context-memory and inter-context scenarios. MMKC-Bench encompasses three types of multimodal knowledge conflicts and includes 1,573 knowledge instances and 3,381 images across 23 broad types, collected through automated pipelines with human verification. We evaluate three representative series of LMMs on both model behavior analysis and conflict detection tasks. Our findings show that while current LMMs are capable of recognizing knowledge conflicts, they tend to favor internal parametric knowledge over external evidence. We hope MMKC-Bench will foster further research in multimodal knowledge conflict and enhance the development of multimodal RAG systems. The source code is available at https://github.com/MLLMKCBENCH/MLLMKC.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 39 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

38 of 39 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  2. 2024Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding12 Nov
  3. 2024Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs10 Oct
  4. 2024A Survey on Evaluation of Multimodal Large Language Models28 Aug
  5. 2024LLaVA-OneVision: Easy Visual Task Transfer6 Aug
  6. 2024The Revolution of Multimodal Large Language Models: A Survey19 Feb
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks21 Dec

Other references · 31

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  9. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  11. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  12. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
19 more
  1. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341
  2. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  3. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  4. 2024VideoAgent: A Memory-augmented Multimodal Agent for Video Understandingcited by 229
  5. 2025OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learningcited by 163
  6. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  7. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 83
  8. 2024ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMcited by 73
  9. 2023Resolving Knowledge Conflicts in Large Language Modelscited by 50
  10. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediacited by 44
  11. 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 43
  12. 2023FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checkingcited by 37
  13. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  14. 2024MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMscited by 32
  15. 2024PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chaincited by 29
  16. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
  17. 2023Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Promptscited by 23
  18. 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledgecited by 23
  19. 2023ContraDoc: Understanding Self-Contradictions in Documents with Large Language Modelscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 14.

19 papers.

Sort:

By area:

  1. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  2. 2025When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorationscited by 7
  3. 2025MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Modelscited by 7
  4. 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledgecited by 5
  5. 2026From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Searchcited by 5
  6. 2025CLASH: A Benchmark for Cross-Modal Contradiction Detectioncited by 3
  7. 2026MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environmentscited by 3
  8. 2026Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Rankingcited by 3
  9. 2026REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignmentcited by 1
  10. 2026MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidencecited by 1
  11. 2026AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Researchcited by 1
  12. 2025KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controlscited by 0
7 more
  1. 2026MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Biascited by 0
  2. 2026MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Partscited by 0
  3. 2026Prior Directions: Why GUI Grounding Gets Locked in the Pastcited by 0
  4. 2026GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMscited by 0
  5. 2026When Text and Numbers Disagree: Evidence Arbitration in Large Language Modelscited by 0
  6. 2026Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agentscited by 0
  7. 2026Why Generate a Click? Plug-in Decision Heads for Web Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict
  2. 2025CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
  3. 2026Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
  4. 2025Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
  5. 2026CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models
  6. 2025SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
  7. 2025CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG
  8. 2024DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models