mlsanityData to 14 Oct 2026

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations

arXiv 2510.06292 ↗First posted 7 Oct 2025cs.CV cs.AIcited by 1

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

While Large Vision-Language Models (LVLMs) achieve strong performance in multimodal tasks, hallucinations continue to hinder their reliability. Among the three categories of hallucinations, which include object, attribute, and relation, relation hallucinations account for the largest proportion but have received the least attention. To address this issue, we propose ChainMPQ (Multi-Perspective Questions guided Interleaved Chain of Image and Text), a training-free method that improves relational inference in LVLMs by utilizing accumulated textual and visual memories. ChainMPQ first extracts subject and object keywords from the question to enhance the corresponding image regions. It then constructs multi-perspective questions that focus on the three core components of a relationship: the subject, the object, and the relation that links them. These questions are sequentially input to the model, with textual and visual memories from earlier steps providing supporting context for subsequent ones, thereby forming an interleaved chain of images and text that guides progressive relational reasoning. Experiments on multiple LVLMs and benchmarks show that ChainMPQ substantially reduces relation hallucinations, while ablation studies further validate the effectiveness of its three core modules.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 32 of its 39 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

32 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models30 Oct

Other references · 31

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2023Qwen Technical Reportcited by 3,344
  7. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  8. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  9. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  10. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  11. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  12. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
19 more
  1. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  2. 2018Object Hallucination in Image Captioningcited by 669
  3. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  4. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 357
  5. 2023MIMIC-IT: Multi-Modal In-Context Instruction Tuningcited by 267
  6. 2024Building and better understanding vision-language models: insights and future directionscited by 173
  7. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinationscited by 104
  8. 2024MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationcited by 88
  9. 2025FG-CLIP: Fine-Grained Visual and Textual Alignmentcited by 81
  10. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 56
  11. 2023Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understandingcited by 46
  12. 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Modelscited by 44
  13. 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resamplingcited by 33
  14. 2024IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Modelscited by 31
  15. 2024Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Modelscited by 30
  16. 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Modelscited by 29
  17. 2025Mind with Eyes: from Language Reasoning to Multimodal Reasoningcited by 22
  18. 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Datacited by 12
  19. 2025Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Promptingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise
  2. 2026RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models
  3. 2024Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
  4. 2024Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
  5. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  6. 2024MMRel: Benchmarking Relation Understanding in Multi-Modal Large Language Models
  7. 2024RelationVLM: Making Large Vision-Language Models Understand Visual Relations
  8. 2024FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability