@inproceedings{ebrahimi-etal-2026-citations,
title = "From Citations to Contributions: {LLM}-Assisted Credit Scoring of Research Articles",
author = "Ebrahimi, Sana and
Shetiya, Suraj and
Asudeh, Abolfazl",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1438/",
doi = "10.18653/2026.findings-emnlp.1438",
pages = "30672--30698",
ISBN = "979-8-89176-462-0",
abstract = "Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper{'}s contribution. We introduce **contribution-based credit scoring** for research articles: a structured citation analysis that decomposes a paper{'}s credit between its own original contribution and the prior work it builds on.\par Motivated by a cooperative-game view of scientific credit, we propose the **contribution tree**, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores.\par Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebrahimi-etal-2026-citations">
<titleInfo>
<title>From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suraj</namePart>
<namePart type="family">Shetiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abolfazl</namePart>
<namePart type="family">Asudeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper’s contribution. We introduce **contribution-based credit scoring** for research articles: a structured citation analysis that decomposes a paper’s credit between its own original contribution and the prior work it builds on.\par Motivated by a cooperative-game view of scientific credit, we propose the **contribution tree**, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores.\par Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics.</abstract>
<identifier type="citekey">ebrahimi-etal-2026-citations</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1438</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1438/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30672</start>
<end>30698</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles
%A Ebrahimi, Sana
%A Shetiya, Suraj
%A Asudeh, Abolfazl
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ebrahimi-etal-2026-citations
%X Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper’s contribution. We introduce **contribution-based credit scoring** for research articles: a structured citation analysis that decomposes a paper’s credit between its own original contribution and the prior work it builds on.\par Motivated by a cooperative-game view of scientific credit, we propose the **contribution tree**, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores.\par Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics.
%R 10.18653/2026.findings-emnlp.1438
%U https://aclanthology.org/2026.findings-emnlp.1438/
%U https://doi.org/10.18653/2026.findings-emnlp.1438
%P 30672-30698
Markdown (Informal)
[From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles](https://aclanthology.org/2026.findings-emnlp.1438/) (Ebrahimi et al., Findings 2026)
ACL