mlsanityData to 7 Oct 2026

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

arXiv 2306.14565 ↗First posted 26 Jun 2023cs.CV cs.AI cs.CEcited by 439

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

Abstract (arXiv)

Despite the promising progress in multi-modal tasks, current large multi-modal models (LMMs) are prone to hallucinating inconsistent descriptions with respect to the associated image and human instructions. This paper addresses this issue by introducing the first large and diverse visual instruction tuning dataset, named Large-scale Robust Visual (LRV)-Instruction. Our dataset comprises 400k visual instructions generated by GPT4, covering 16 vision-and-language tasks with open-ended instructions and answers. Unlike existing studies that primarily focus on positive instruction samples, we design LRV-Instruction to include both positive and negative instructions for more robust visual instruction tuning. Our negative instructions are designed at three semantic levels: (i) Nonexistent Object Manipulation, (ii) Existent Object Manipulation and (iii) Knowledge Manipulation. To efficiently measure the hallucination generated by LMMs, we propose GPT4-Assisted Visual Instruction Evaluation (GAVIE), a stable approach to evaluate visual instruction tuning like human experts. GAVIE does not require human-annotated groundtruth answers and can adapt to diverse instruction formats. We conduct comprehensive experiments to investigate the hallucination of LMMs. Our results demonstrate existing LMMs exhibit significant hallucinations when presented with our negative instructions, particularly Existent Object and Knowledge Manipulation instructions. Moreover, we successfully mitigate hallucination by finetuning MiniGPT4 and mPLUG-Owl on LRV-Instruction while improving performance on several public datasets compared to state-of-the-art methods. Additionally, we observed that a balanced ratio of positive and negative instances in the training data leads to a more robust model. Code and data are available at https://github.com/FuxiaoLiu/LRV-Instruction.

Key facts. Cited by 439 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 38 of its 50 references that are in the map. First posted on arXiv 26 Jun 2023.

Builds on

38 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  8. 2023Visual Instruction Tuningcited by 7,792
  9. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  11. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  12. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
25 more
  1. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2023A Survey of Large Language Modelscited by 2,537
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  6. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  7. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  8. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  9. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  10. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  11. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  12. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  13. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
  14. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  15. 2023Instruction Tuning with GPT-4cited by 676
  16. 2018Object Hallucination in Image Captioningcited by 661
  17. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  18. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 536
  19. 2021WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learningcited by 285
  20. 2023MultiModal-GPT: A Vision and Language Model for Dialogue with Humanscited by 255
  21. 2020Visual News: Benchmark and Challenges in News Image Captioningcited by 121
  22. 2022GRiT: A Generative Region-to-text Transformer for Object Understandingcited by 119
  23. 2021BERT: A Review of Applications in Natural Language Processing and Understandingcited by 109
  24. 2023COVID-VTS: Fact Extraction and Verification on Short Video Platformscited by 15
  25. 2023DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documentscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 23; 2024: 162; 2025: 161; 2026: 93.

439 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  3. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  4. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  5. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  6. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
  7. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  8. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  9. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  10. 2023Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understandingcited by 368
  11. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  12. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
38 more
  1. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  2. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  3. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  4. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  5. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 254
  6. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  7. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 223
  8. 2024NVILA: Efficient Frontier Visual Language Modelscited by 206
  9. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  10. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decodingcited by 198
  11. 2024An Introduction to Vision-Language Modelingcited by 175
  12. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMscited by 174
  13. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 171
  14. 2024Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lenscited by 139
  15. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  16. 2024The Revolution of Multimodal Large Language Models: A Surveycited by 134
  17. 2023Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challengescited by 131
  18. 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 127
  19. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 125
  20. 2023Hallucination Augmented Contrastive Learning for Multimodal Large Language Modelcited by 119
  21. 2024IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decodingcited by 118
  22. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 98
  23. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inferencecited by 97
  24. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revisioncited by 96
  25. 2024Efficient Multimodal Large Language Models: A Surveycited by 95
  26. 2025Self-Rewarding Vision-Language Model via Reasoning Decompositioncited by 95
  27. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Modelscited by 90
  28. 2024A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendationscited by 84
  29. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 81
  30. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attentioncited by 74
  31. 2024Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMscited by 73
  32. 2024Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Modelscited by 72
  33. 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
  34. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 71
  35. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 69
  36. 2024Visual Hallucinations of Multi-modal Large Language Modelscited by 68
  37. 2024BRAVE: Broadening the visual encoding of vision-language modelscited by 68
  38. 2024VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understandingcited by 65

50 most cited of 439 All 439 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
  2. 2025Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
  3. 2026Fine-Grained Multi Image Object Hallucination Benchmark
  4. 2023Mitigating Hallucination in Visual Language Models with Visual Supervision
  5. 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
  6. 2024From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
  7. 2025PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
  8. 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation