# ISQA: Informative Factuality Feedback for Scientific Summarization

Source: [ISQA: Informative Factuality Feedback for Scientific Summarization](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b00>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:38:38.445Z

Authors: Zekai Li, Yanxia Qin, Qian Liu, Min-Yen Kan

Published: 2024-04-20T03:16:13.000Z

## Abstract

We propose Iterative Facuality Refining on Informative Scientific Question-Answering (ISQA) feedback\\footnote{Code is available at \\url{https://github.com/lizekai-richard/isqa}}, a method following human learning theories that employs model-generated feedback consisting of both positive and negative information. Through iterative refining of summaries, it probes for the underlying rationale of statements to enhance the factuality of scientific summarization. ISQA does this in a fine-grained manner by asking a summarization agent to reinforce validated statements in positive feedback and fix incorrect ones in negative feedback. Our findings demonstrate that the ISQA feedback mechanism significantly improves the factuality of various open-source LLMs on the summarization task, as evaluated across multiple scientific datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.13246>)

[PDF](<https://arxiv.org/pdf/2404.13246.pdf>)
