Pith. sign in

REVIEW 1 cited by

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.01002 v2 pith:WU3XJCXH submitted 2024-03-01 cs.CL cs.AI

classification cs.CLcs.AI
keywords clinicalevaluationtextstructuringsummariesattributehealthhuman
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Summarizing clinical text is crucial in health decision-support and clinical research. Large language models (LLMs) have shown the potential to generate accurate clinical text summaries, but still struggle with issues regarding grounding and evaluation, especially in safety-critical domains such as health. Holistically evaluating text summaries is challenging because they may contain unsubstantiated information. Here, we explore a general mitigation framework using Attribute Structuring (AS), which structures the summary evaluation process. It decomposes the evaluation process into a grounded procedure that uses an LLM for relatively simple structuring and scoring tasks, rather than the full task of holistic summary evaluation. Experiments show that AS consistently improves the correspondence between human annotations and automated metrics in clinical text summarization. Additionally, AS yields interpretations in the form of a short text span corresponding to each output, which enables efficient human auditing, paving the way towards trustworthy evaluation of clinical information in resource-constrained scenarios. We release our code, prompts, and an open-source benchmark at https://github.com/microsoft/attribute-structuring.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities

    cs.HC 2024-11 conditional novelty 6.0 of 10

    ComViewer adds zoomable topic circles, support-type filters, and LLM-based note-taking and questioning to online mental health communities, and a within-subjects study shows more informational support and engagement v...

Pith tools