@inproceedings{azime-etal-2025-evaluation,
title = "Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing",
author = "Azime, Israel Abebe and
Belay, Tadesse Destaw and
Tonja, Atnafu Lambebo",
editor = "Zhang, Chen and
Allaway, Emily and
Shen, Hua and
Miculicich, Lesly and
Li, Yinqiao and
M'hamdi, Meryem and
Limkonchotiwat, Peerat and
Bai, Richard He and
T.y.s.s., Santosh and
Han, Sophia Simeng and
Thapa, Surendrabikram and
Rim, Wiem Ben",
booktitle = "Proceedings of the 9th Widening NLP Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.winlp-main.36/",
pages = "242--250",
ISBN = "979-8-89176-351-7",
abstract = "Large Language Models (LLMs) powered with argentic capabilities are able to do knowledge-intensive tasks without human involvement. A prime example of this tool is Deep research with the capability to browse the web, extract information and generate multi-page reports.In this work, we introduce an evaluation sheet that can be used for assessing the capability of Deep Research tools. In addition, we selected academic survey writing as a use case task and evaluated output reports based on the evaluation sheet we introduced. Our findings show the need to have carefully crafted evaluation standards. The evaluation done on OpenAI{`}s Deep Search and Google{'}s Deep Search in generating an academic survey showed the huge gap between search engines and standalone Deep Research tools, as well as the shortcomings in representing the targeted area."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azime-etal-2025-evaluation">
<titleInfo>
<title>Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Israel</namePart>
<namePart type="given">Abebe</namePart>
<namePart type="family">Azime</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="given">Destaw</namePart>
<namePart type="family">Belay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</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 9th Widening NLP Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Allaway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lesly</namePart>
<namePart type="family">Miculicich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinqiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">M’hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">He</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.y.s.s.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="given">Simeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiem</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-351-7</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) powered with argentic capabilities are able to do knowledge-intensive tasks without human involvement. A prime example of this tool is Deep research with the capability to browse the web, extract information and generate multi-page reports.In this work, we introduce an evaluation sheet that can be used for assessing the capability of Deep Research tools. In addition, we selected academic survey writing as a use case task and evaluated output reports based on the evaluation sheet we introduced. Our findings show the need to have carefully crafted evaluation standards. The evaluation done on OpenAI‘s Deep Search and Google’s Deep Search in generating an academic survey showed the huge gap between search engines and standalone Deep Research tools, as well as the shortcomings in representing the targeted area.</abstract>
<identifier type="citekey">azime-etal-2025-evaluation</identifier>
<location>
<url>https://aclanthology.org/2025.winlp-main.36/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>242</start>
<end>250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing
%A Azime, Israel Abebe
%A Belay, Tadesse Destaw
%A Tonja, Atnafu Lambebo
%Y Zhang, Chen
%Y Allaway, Emily
%Y Shen, Hua
%Y Miculicich, Lesly
%Y Li, Yinqiao
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.y.s.s., Santosh
%Y Han, Sophia Simeng
%Y Thapa, Surendrabikram
%Y Rim, Wiem Ben
%S Proceedings of the 9th Widening NLP Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-351-7
%F azime-etal-2025-evaluation
%X Large Language Models (LLMs) powered with argentic capabilities are able to do knowledge-intensive tasks without human involvement. A prime example of this tool is Deep research with the capability to browse the web, extract information and generate multi-page reports.In this work, we introduce an evaluation sheet that can be used for assessing the capability of Deep Research tools. In addition, we selected academic survey writing as a use case task and evaluated output reports based on the evaluation sheet we introduced. Our findings show the need to have carefully crafted evaluation standards. The evaluation done on OpenAI‘s Deep Search and Google’s Deep Search in generating an academic survey showed the huge gap between search engines and standalone Deep Research tools, as well as the shortcomings in representing the targeted area.
%U https://aclanthology.org/2025.winlp-main.36/
%P 242-250
Markdown (Informal)
[Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing](https://aclanthology.org/2025.winlp-main.36/) (Azime et al., WiNLP 2025)
ACL