Papers/2608.16971
🧪 Test?View on arXiv

FedPref: Federated Preference Learning for Structured Radiology Report Extraction

Not provided in the abstract

federated learningmedical AIdata privacynatural language processing
2608.16971
Builder Relevance
80%
2h ago

Abstract

FedPref enables institutions with unequal, unpooled data to collaboratively train models for structured radiology report extraction without sharing sensitive data.

Reality Card

Core Claim

FedPref improves client-mean F1 by 2.49 points and worst-site F1 by 9.10 points compared to isolated training, particularly benefiting sites with less data.

Method / Result

FedPref achieves a client-mean F1 of 68.68 on a locked, manually validated gold test set.

Limitations

The paper does not specify the authors, which may limit reproducibility and transparency.

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