@inproceedings{spangher-etal-2025-novel,
title = "A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting",
author = "Spangher, Alexander and
Huang, Tenghao and
Huang, Yiqin and
Spangher, Lucas and
Min, Sewon and
Dredze, Mark",
editor = "Shi, Weijia and
Yu, Wenhao and
Asai, Akari and
Jiang, Meng and
Durrett, Greg and
Hajishirzi, Hannaneh and
Zettlemoyer, Luke",
booktitle = "Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.knowledgenlp-1.18/",
doi = "10.18653/v1/2025.knowledgenlp-1.18",
pages = "180--204",
ISBN = "979-8-89176-229-9",
abstract = "Multi-document retrieval approaches often overlook the ways different retrievals complement each other when addressing complex queries. In this work, we study journalist source selection in news article writing and examine the discourse roles that different sources serve when paired together, finding that discourse function (not simply informational content) is an important component of source usage. Then, we introduce a novel IR task to benchmark how well language models can reason about this narrative process. We extract a journalist{'}s initial query and the sources they used from news articles and aim to recover the sources that support this query. We demonstrate that large language models (LLMs) can be employed in multi-step query planning, identifying informational gaps and enhancing retrieval performance, but current approaches to interleave queries fall short. By training auxiliary discourse planners and incorporating this information into LLMs, we enhance query planning, achieving a significant 5{\%} improvement in precision and a 2{\%} increase in F1 score over the previous SOTA, all while maintaining recall."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spangher-etal-2025-novel">
<titleInfo>
<title>A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Spangher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tenghao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Spangher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dredze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-229-9</identifier>
</relatedItem>
<abstract>Multi-document retrieval approaches often overlook the ways different retrievals complement each other when addressing complex queries. In this work, we study journalist source selection in news article writing and examine the discourse roles that different sources serve when paired together, finding that discourse function (not simply informational content) is an important component of source usage. Then, we introduce a novel IR task to benchmark how well language models can reason about this narrative process. We extract a journalist’s initial query and the sources they used from news articles and aim to recover the sources that support this query. We demonstrate that large language models (LLMs) can be employed in multi-step query planning, identifying informational gaps and enhancing retrieval performance, but current approaches to interleave queries fall short. By training auxiliary discourse planners and incorporating this information into LLMs, we enhance query planning, achieving a significant 5% improvement in precision and a 2% increase in F1 score over the previous SOTA, all while maintaining recall.</abstract>
<identifier type="citekey">spangher-etal-2025-novel</identifier>
<identifier type="doi">10.18653/v1/2025.knowledgenlp-1.18</identifier>
<location>
<url>https://aclanthology.org/2025.knowledgenlp-1.18/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>180</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting
%A Spangher, Alexander
%A Huang, Tenghao
%A Huang, Yiqin
%A Spangher, Lucas
%A Min, Sewon
%A Dredze, Mark
%Y Shi, Weijia
%Y Yu, Wenhao
%Y Asai, Akari
%Y Jiang, Meng
%Y Durrett, Greg
%Y Hajishirzi, Hannaneh
%Y Zettlemoyer, Luke
%S Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, USA
%@ 979-8-89176-229-9
%F spangher-etal-2025-novel
%X Multi-document retrieval approaches often overlook the ways different retrievals complement each other when addressing complex queries. In this work, we study journalist source selection in news article writing and examine the discourse roles that different sources serve when paired together, finding that discourse function (not simply informational content) is an important component of source usage. Then, we introduce a novel IR task to benchmark how well language models can reason about this narrative process. We extract a journalist’s initial query and the sources they used from news articles and aim to recover the sources that support this query. We demonstrate that large language models (LLMs) can be employed in multi-step query planning, identifying informational gaps and enhancing retrieval performance, but current approaches to interleave queries fall short. By training auxiliary discourse planners and incorporating this information into LLMs, we enhance query planning, achieving a significant 5% improvement in precision and a 2% increase in F1 score over the previous SOTA, all while maintaining recall.
%R 10.18653/v1/2025.knowledgenlp-1.18
%U https://aclanthology.org/2025.knowledgenlp-1.18/
%U https://doi.org/10.18653/v1/2025.knowledgenlp-1.18
%P 180-204
Markdown (Informal)
[A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting](https://aclanthology.org/2025.knowledgenlp-1.18/) (Spangher et al., KnowledgeNLP 2025)
ACL