@inproceedings{chen-etal-2025-drafts,
title = "Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts",
author = "Chen, Danqing and
Weber, Ingo and
Dietrich, Felix",
editor = "Akter, Mousumi and
Chowdhury, Tahiya and
Eger, Steffen and
Leiter, Christoph and
Opitz, Juri and
{\c{C}}ano, Erion",
booktitle = "Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.eval4nlp-1.6/",
pages = "66--84",
ISBN = "979-8-89176-305-0",
abstract = "This study explores the potential of a lightweight, open-source Large Language Model (LLM), demonstrating how its integration with Retrieval-Augmented Generation (RAG) can support cost-effective evaluation of revision quality and writing style differentiation. By retrieving reference documents from a carefully chosen and constructed corpus of peer-reviewed conference proceedings, our framework leverages few-shot in-context learning to track manuscript revisions and venue-specific writing styles. We demonstrate that the LLM-based evaluation aligns closely with human revision histories{---}consistently recognizing quality improvements across revision stages and distinguishing writing styles associated with different conference venues. These findings highlight how a carefully designed evaluation framework, integrated with adequate, representative data, can advance automated assessment of scientific writing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-drafts">
<titleInfo>
<title>Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danqing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingo</namePart>
<namePart type="family">Weber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Dietrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mousumi</namePart>
<namePart type="family">Akter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahiya</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Leiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erion</namePart>
<namePart type="family">Çano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-305-0</identifier>
</relatedItem>
<abstract>This study explores the potential of a lightweight, open-source Large Language Model (LLM), demonstrating how its integration with Retrieval-Augmented Generation (RAG) can support cost-effective evaluation of revision quality and writing style differentiation. By retrieving reference documents from a carefully chosen and constructed corpus of peer-reviewed conference proceedings, our framework leverages few-shot in-context learning to track manuscript revisions and venue-specific writing styles. We demonstrate that the LLM-based evaluation aligns closely with human revision histories—consistently recognizing quality improvements across revision stages and distinguishing writing styles associated with different conference venues. These findings highlight how a carefully designed evaluation framework, integrated with adequate, representative data, can advance automated assessment of scientific writing.</abstract>
<identifier type="citekey">chen-etal-2025-drafts</identifier>
<location>
<url>https://aclanthology.org/2025.eval4nlp-1.6/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>66</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts
%A Chen, Danqing
%A Weber, Ingo
%A Dietrich, Felix
%Y Akter, Mousumi
%Y Chowdhury, Tahiya
%Y Eger, Steffen
%Y Leiter, Christoph
%Y Opitz, Juri
%Y Çano, Erion
%S Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-305-0
%F chen-etal-2025-drafts
%X This study explores the potential of a lightweight, open-source Large Language Model (LLM), demonstrating how its integration with Retrieval-Augmented Generation (RAG) can support cost-effective evaluation of revision quality and writing style differentiation. By retrieving reference documents from a carefully chosen and constructed corpus of peer-reviewed conference proceedings, our framework leverages few-shot in-context learning to track manuscript revisions and venue-specific writing styles. We demonstrate that the LLM-based evaluation aligns closely with human revision histories—consistently recognizing quality improvements across revision stages and distinguishing writing styles associated with different conference venues. These findings highlight how a carefully designed evaluation framework, integrated with adequate, representative data, can advance automated assessment of scientific writing.
%U https://aclanthology.org/2025.eval4nlp-1.6/
%P 66-84
Markdown (Informal)
[Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts](https://aclanthology.org/2025.eval4nlp-1.6/) (Chen et al., Eval4NLP 2025)
ACL