Actionable Feedback: Improving Model Capabilities from User Edit Data on Clinical Documentation

Not provided in the abstract

fine-tuningclinical documentationuser feedback

2611.12904

Builder Relevance

80%

17h ago

Abstract

The paper discusses a method to improve large language models in clinical documentation by filtering clinician edits to identify actionable feedback.

Reality Card

Core Claim

The proposed method of filtering clinician edits significantly improves model alignment with clinician expectations while maintaining input context fidelity.

Method / Result

Naive fine-tuning on raw edited output increases ungrounded content by over 45%, while the filtering approach enhances clinician-alignment metrics.

Limitations

Real clinician edits are not publicly available, which may limit the generalizability of the findings.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers