ReasonEdit: Editing Vision-Language Models using Human Reasoning

ReasonEdit is a new editor for vision‑language models that allows users to provide reasoning explanations during the editing process. It stores human reasoning in a codebook and retrieves relevant facts at inference time using a topology‑balanced multimodal embedding approach inspired by network science. Experiments on four VLMs and multiple rationale‑based visual question answering datasets show that incorporating human reasoning leads to state‑of‑the‑art editing performance and better generalization.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• rag
• nlp
• multimodal
• benchmarks