arXiv Artificial Intelligence

ReasonEdit: Editing Vision-Language Models using Human Reasoning

16 days ago 25.08.2026 07:00 👁 1 views
ReasonEdit: Editing Vision-Language Models using Human Reasoning

Quick summary

arXiv:2602.02408v5 Announce Type: replace-cross Abstract: 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 dur

Key takeaways

  • arXiv:2602.02408v5 Announce Type: replace-cross Abstract: 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.

Why it matters

“ReasonEdit: Editing Vision-Language Models using Human Reasoning” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗