mlsanityData to 7 Oct 2026

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models

arXiv 2408.09429 ↗First posted 18 Aug 2024cs.LG cs.CL cs.CVcited by 30

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinations that require advanced reasoning. Current benchmarks for relation hallucinations lack detailed evaluation and effective mitigation, and their datasets often suffer from biases due to systematic annotation processes. To address these challenges, we introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples. We provide a systematic definition of relation hallucinations, integrating perceptive and cognitive perspectives, and construct a relation-based corpus using the Visual Genome scene graph dataset. Our comparative evaluation reveals significant limitations in current MLLMs' ability to handle relation hallucinations. Additionally, we propose a novel confidence-based mitigation strategy, which reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. Our work offers valuable insights for achieving trustworthy multimodal intelligence.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 26 of its 53 references that are in the map. First posted on arXiv 18 Aug 2024.

Builds on

26 of 53 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models24 Jun
  2. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback1 Dec
  3. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  4. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  5. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation13 Nov

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  9. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  10. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
  11. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  12. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
9 more
  1. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 367
  2. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  3. 2018Exploring Visual Relationship for Image Captioningcited by 215
  4. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  5. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
  6. 2023UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Webcited by 77
  7. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  8. 2023Word Embeddings Are Steers for Language Modelscited by 70
  9. 2023Do Large Language Models Know about Facts?cited by 49

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 10; 2026: 12.

30 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2024Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Modelscited by 72
  3. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  4. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  5. 2025Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retentioncited by 45
  6. 2024Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causalitycited by 42
  7. 2024ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detectioncited by 37
  8. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  9. 2025DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruningcited by 19
  10. 2025GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detectioncited by 17
  11. 2025GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoningcited by 13
  12. 2025CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMscited by 13
18 more
  1. 2024ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Modelscited by 8
  2. 2024Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Modelscited by 7
  3. 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigationcited by 7
  4. 2025Measuring Epistemic Humility in Multimodal Large Language Modelscited by 4
  5. 2026CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Modelscited by 3
  6. 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Modelscited by 3
  7. 2026Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearningcited by 3
  8. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  9. 2026MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialoguecited by 2
  10. 2025ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinationscited by 1
  11. 2026Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Timecited by 1
  12. 2026When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMscited by 1
  13. 2025Spatial Knowledge Graph-Guided Multimodal Synthesiscited by 0
  14. 2026Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigationcited by 0
  15. 2026When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noisecited by 0
  16. 2026Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoningcited by 0
  17. 2026The Safeguard Worked. Is the LLM System Safer?cited by 0
  18. 2026MLLMs Hallucinate when Information Distribution Drifts in Synergy Headscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
  2. 2026KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation
  3. 2025MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
  4. 2024Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
  5. 2024HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
  6. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
  7. 2025MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models
  8. 2025OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models