@inproceedings{sinha-2025-qa,
title = "{QA}-prompting: Improving Summarization with Large Language Models using Question-Answering",
author = "Sinha, Neelabh",
editor = "Dong, Yue and
Xiao, Wen and
Zhang, Haopeng and
Zhang, Rui and
Ernst, Ori and
Wang, Lu and
Liu, Fei",
booktitle = "Proceedings of The 5th New Frontiers in Summarization Workshop",
month = nov,
year = "2025",
address = "Hybrid",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.newsum-main.14/",
pages = "199--212",
ISBN = "979-8-89176-337-1",
abstract = "Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases, leading to suboptimal extraction of critical information. There are techniques to improve this with fine-tuning, pipelining, or using complex techniques, which have their own challenges. To solve these challenges, we propose QA-prompting - a simple prompting method for summarization that utilizes question-answering as an intermediate step prior to summary generation. Our method extracts key information and enriches the context of text to mitigate positional biases and improve summarization in a single LM call per task without requiring fine-tuning or pipelining. Experiments on multiple datasets belonging to different domains using ten state-of-the-art pre-trained models demonstrate that QA-prompting outperforms baseline and other state-of-the-art methods, achieving up to 29{\%} improvement in ROUGE scores. This provides an effective and scalable solution for summarization and highlights the importance of domain-specific question selection for optimal performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sinha-2025-qa">
<titleInfo>
<title>QA-prompting: Improving Summarization with Large Language Models using Question-Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neelabh</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 5th New Frontiers in Summarization Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haopeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ori</namePart>
<namePart type="family">Ernst</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-337-1</identifier>
</relatedItem>
<abstract>Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases, leading to suboptimal extraction of critical information. There are techniques to improve this with fine-tuning, pipelining, or using complex techniques, which have their own challenges. To solve these challenges, we propose QA-prompting - a simple prompting method for summarization that utilizes question-answering as an intermediate step prior to summary generation. Our method extracts key information and enriches the context of text to mitigate positional biases and improve summarization in a single LM call per task without requiring fine-tuning or pipelining. Experiments on multiple datasets belonging to different domains using ten state-of-the-art pre-trained models demonstrate that QA-prompting outperforms baseline and other state-of-the-art methods, achieving up to 29% improvement in ROUGE scores. This provides an effective and scalable solution for summarization and highlights the importance of domain-specific question selection for optimal performance.</abstract>
<identifier type="citekey">sinha-2025-qa</identifier>
<location>
<url>https://aclanthology.org/2025.newsum-main.14/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>199</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QA-prompting: Improving Summarization with Large Language Models using Question-Answering
%A Sinha, Neelabh
%Y Dong, Yue
%Y Xiao, Wen
%Y Zhang, Haopeng
%Y Zhang, Rui
%Y Ernst, Ori
%Y Wang, Lu
%Y Liu, Fei
%S Proceedings of The 5th New Frontiers in Summarization Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Hybrid
%@ 979-8-89176-337-1
%F sinha-2025-qa
%X Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases, leading to suboptimal extraction of critical information. There are techniques to improve this with fine-tuning, pipelining, or using complex techniques, which have their own challenges. To solve these challenges, we propose QA-prompting - a simple prompting method for summarization that utilizes question-answering as an intermediate step prior to summary generation. Our method extracts key information and enriches the context of text to mitigate positional biases and improve summarization in a single LM call per task without requiring fine-tuning or pipelining. Experiments on multiple datasets belonging to different domains using ten state-of-the-art pre-trained models demonstrate that QA-prompting outperforms baseline and other state-of-the-art methods, achieving up to 29% improvement in ROUGE scores. This provides an effective and scalable solution for summarization and highlights the importance of domain-specific question selection for optimal performance.
%U https://aclanthology.org/2025.newsum-main.14/
%P 199-212
Markdown (Informal)
[QA-prompting: Improving Summarization with Large Language Models using Question-Answering](https://aclanthology.org/2025.newsum-main.14/) (Sinha, NewSum 2025)
ACL