mlsanityData to 14 Oct 2026

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models

arXiv 2410.23114 ↗First posted 30 Oct 2024cs.CV cs.AI cs.CLcited by 7

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

Despite the outstanding performance in vision-language reasoning, Large Vision-Language Models (LVLMs) might generate hallucinated contents that do not exist in the given image. Most existing LVLM hallucination benchmarks are constrained to evaluate the object-related hallucinations. However, the potential hallucination on the relations between two objects, i.e., relation hallucination, still lacks investigation. To remedy that, we design a unified framework to measure the object and relation hallucination in LVLMs simultaneously. The core idea of our framework is to evaluate hallucinations via (object, relation, object) triplets extracted from LVLMs' responses, making it easily generalizable to different vision-language tasks. Based on our framework, we further introduce Tri-HE, a novel Triplet-level Hallucination Evaluation benchmark which can be used to study both object and relation hallucination at the same time. With comprehensive evaluations on Tri-HE, we observe that the relation hallucination issue is even more serious than object hallucination among existing LVLMs, highlighting a previously neglected problem towards reliable LVLMs. Moreover, based on our findings, we design a simple training-free approach that effectively mitigates hallucinations for LVLMs. Our dataset and code for the reproduction of our experiments are available publicly at https://github.com/wujunjie1998/Tri-HE.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 43 of its 62 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

43 of 62 references.

References · 43

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  7. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  10. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  11. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  12. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
31 more
  1. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 688
  2. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  3. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 478
  4. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
  5. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  6. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 316
  7. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 300
  8. 2023MagicDrive: Street View Generation with Diverse 3D Geometry Controlcited by 252
  9. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 225
  10. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decodingcited by 174
  11. 2024Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformationcited by 124
  12. 2023Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuningcited by 106
  13. 2022CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Drivingcited by 100
  14. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Modelscited by 99
  15. 2024Automated Evaluation of Large Vision-Language Models on Self-driving Corner Casescited by 77
  16. 2024Unified Hallucination Detection for Multimodal Large Language Modelscited by 75
  17. 2024MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenescited by 71
  18. 2024Multi-Object Hallucination in Vision-Language Modelscited by 60
  19. 2023GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generationcited by 56
  20. 2024Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Modelscited by 47
  21. 2024EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotionscited by 45
  22. 2021MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Drivingcited by 41
  23. 2023Mixed Autoencoder for Self-supervised Visual Representation Learningcited by 38
  24. 2023Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysiscited by 35
  25. 2024DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perceptioncited by 32
  26. 2024Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Modelscited by 30
  27. 2023Implicit Concept Removal of Diffusion Modelscited by 23
  28. 2022Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routingcited by 18
  29. 2024Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Expertscited by 16
  30. 2024Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignmentcited by 10
  31. 2024Skip n: A Simple Method to Reduce Hallucination in Large Vision-Language Modelscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Interventioncited by 11
  2. 2025ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Drivingcited by 5
  3. 2026FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMscited by 4
  4. 2025Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignmentcited by 3
  5. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  6. 2025ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinationscited by 1
  7. 2026Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models
  2. 2025A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
  3. 2024Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
  4. 2024VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models
  5. 2025Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities
  6. 2024Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
  7. 2024Mitigating Multilingual Hallucination in Large Vision-Language Models
  8. 2024Hallucination of Multimodal Large Language Models: A Survey