ERA: Evidence-Based Reasoning and Augmentation for Open-Vocabulary Medical Vision

Yu Fang, Pan Tao, Xin Wang, Xin Yang, Fan Min, Tianrui LiOpenReview 2026 · Submission to ICLR 2026 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Vision-Language Models (VLMs) have shown great potential in the domain of open-vocabulary medical imaging tasks. However, their reliance on implicit correlations instead of explicit evidence leads to unreliable localization and unexplainable reasoning processes. To address these challenges, we introduce ERA (Evidence-Based Reasoning and Augmentation), a novel framework that transforms VLMs from implicit guessers into explicit reasoners for medical imaging. ERA leverages Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) to construct a traceable reasoning path from evidence to results. This framework requires no additional training and can be readily applied on top of any existing Vision-Language Model. Evaluated across multiple challenging medical imaging benchmarks, ERA's performance is comparable to fully-supervised specialist models and significantly surpasses current open-vocabulary baseline methods. ERA provides an effective pathway for building reliable clinical Vision-Language Models.
BibTeX
@misc{fang2026era,
  author = {Yu Fang and Pan Tao and Xin Wang and Xin Yang and Fan Min and Tianrui Li},
  title = {{ERA: Evidence-Based Reasoning and Augmentation for Open-Vocabulary Medical Vision}},
  year = {2026},
  url = {https://openreview.net/forum?id=qrSYVqY367},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}

Loading related content...

Figure