mlsanityData to 7 Oct 2026

AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models

arXiv 2406.10900 ↗First posted 16 Jun 2024cs.CV cs.CLcited by 30

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

Abstract (arXiv)

Large vision-language models (LVLMs) are prone to hallucinations, where certain contextual cues in an image can trigger the language module to produce overconfident and incorrect reasoning about abnormal or hypothetical objects. While some benchmarks have been developed to investigate LVLM hallucinations, they often rely on hand-crafted corner cases whose failure patterns may not generalize well. Additionally, fine-tuning on these examples could undermine their validity. To address this, we aim to scale up the number of cases through an automated approach, reducing human bias in crafting such corner cases. This motivates the development of AutoHallusion, the first automated benchmark generation approach that employs several key strategies to create a diverse range of hallucination examples. Our generated visual-question pairs pose significant challenges to LVLMs, requiring them to overcome contextual biases and distractions to arrive at correct answers. AutoHallusion enables us to create new benchmarks at the minimum cost and thus overcomes the fragility of hand-crafted benchmarks. It also reveals common failure patterns and reasons, providing key insights to detect, avoid, or control hallucinations. Comprehensive evaluations of top-tier LVLMs, e.g., GPT-4V(ision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, show a 97.7% and 98.7% success rate of hallucination induction on synthetic and real-world datasets of AutoHallusion, paving the way for a long battle against hallucinations. The codebase and data can be accessed at https://github.com/wuxiyang1996/AutoHallusion.

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 60 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

26 of 60 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models24 Feb
  2. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  3. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models23 Oct
  4. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
  5. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 21

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  7. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  8. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  9. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  10. 2018Object Hallucination in Image Captioningcited by 661
  11. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  12. 2023M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuningcited by 126
9 more
  1. 2023ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Modelscited by 116
  2. 2024How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Promptscited by 47
  3. 2023Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPTcited by 28
  4. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  5. 2023Mitigating Open-Vocabulary Caption Hallucinationscited by 18
  6. 2023LLM-Based Human-Robot Collaboration Framework for Manipulation Taskscited by 17
  7. 2024On the Vulnerability of LLM/VLM-Controlled Roboticscited by 15
  8. 2024The Instinctive Bias: Spurious Images lead to Illusion in MLLMscited by 11
  9. 2024LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 16; 2026: 9.

30 papers.

Sort:

By area:

  1. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  2. 2025A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challengescited by 46
  3. 2025VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understandingcited by 32
  4. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  5. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  6. 2024WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agentscited by 24
  7. 2024DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedbackcited by 23
  8. 2025TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrationscited by 7
  9. 2025Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognitioncited by 7
  10. 2026HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Modelscited by 7
  11. 2025WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agentscited by 5
  12. 2025MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Modelscited by 5
18 more
  1. 2026Improving Visual Reasoning with Iterative Evidence Refinementcited by 5
  2. 2025GHOST: Hallucination-Inducing Image Generation for Multimodal LLMscited by 4
  3. 2026Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarkingcited by 4
  4. 2024FIHA: Autonomous Hallucination Evaluation in Vision-Language Models with Davidson Scene Graphscited by 3
  5. 2025SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflowcited by 2
  6. 2025Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Modelcited by 2
  7. 2025From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Modelscited by 2
  8. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  9. 2025Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Modelscited by 1
  10. 2025Leveraging NTPs for Efficient Hallucination Detection in VLMscited by 1
  11. 2025Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilitiescited by 1
  12. 2025HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restorationcited by 1
  13. 2026No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairscited by 1
  14. 2026Unified Hallucination Fuzzing for Multimodal Large Language Modelscited by 1
  15. 2026CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steeringcited by 0
  16. 2026What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustnesscited by 0
  17. 2026MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Biascited by 0
  18. 2026Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  2. 2026Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
  3. 2024Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
  4. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations
  5. 2025A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
  6. 2024H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models
  7. 2024Visual Hallucination: Definition, Quantification, and Prescriptive Remediations
  8. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering