mlsanityData to 7 Oct 2026

ReasonEdit: Editing Vision-Language Models using Human Reasoning

arXiv 2602.02408 ↗First posted 2 Feb 2026cs.CV cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically require humans and models to reason about images. We therefore propose ReasonEdit, the first VLM editor to let users explain their reasoning during editing, introducing a new, practical model editing setup. ReasonEdit continuously stores human reasoning in a codebook, and retrieves only relevant facts during inference using a novel topology-balanced multimodal embedding method inspired by network science. Across four VLMs on multiple rationale-based visual question answering datasets, ReasonEdit achieves state-of-the-art editing performance, ultimately showing that using human reasoning during editing greatly improves edit generalization.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 39 of its 46 references that are in the map. First posted on arXiv 2 Feb 2026.

Builds on

39 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Improve Vision Language Model Chain-of-thought Reasoning21 Oct

Other references · 38

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  7. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  9. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  10. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  11. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  12. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
26 more
  1. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  2. 2021Editing Factual Knowledge in Language Modelscited by 548
  3. 2021Fast Model Editing at Scalecited by 491
  4. 2022Memory-Based Model Editing at Scalecited by 443
  5. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  6. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 297
  7. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 274
  8. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  9. 2023Generating Images with Multimodal Language Modelscited by 259
  10. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  11. 2016FVQA: Fact-based Visual Question Answeringcited by 181
  12. 2020Editable Neural Networkscited by 154
  13. 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Reviewcited by 121
  14. 2023Contextual Object Detection with Multimodal Large Language Modelscited by 100
  15. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  16. 2023Can We Edit Multimodal Large Language Models?cited by 44
  17. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  18. 2024Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answeringcited by 31
  19. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  20. 2024MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistencycited by 22
  21. 2024Bridging Different Language Models and Generative Vision Models for Text-to-Image Generationcited by 17
  22. 2024Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Expertscited by 14
  23. 2024Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Modelscited by 9
  24. 2025BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editingcited by 7
  25. 2022Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysiscited by 5
  26. 2024Select-Mosaic: Data Augmentation Method for Dense Small Object Scenescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Models
  2. 2026ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning
  3. 2026ETCHR: Editing To Clarify and Harness Reasoning
  4. 2024EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing
  5. 2024Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
  6. 2025Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing
  7. 2025Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
  8. 2026CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning