@inproceedings{rawte-etal-2025-document,
title = "Document Attribution: Examining Citation Relationships using Large Language Models",
author = "Rawte, Vipula and
Rossi, Ryan A. and
Dernoncourt, Franck and
Lipka, Nedim",
editor = "Ghosal, Tirthankar and
Mayr, Philipp and
Singh, Amanpreet and
Naik, Aakanksha and
Rehm, Georg and
Freitag, Dayne and
Li, Dan and
Schimmler, Sonja and
De Waard, Anita",
booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sdp-1.12/",
doi = "10.18653/v1/2025.sdp-1.12",
pages = "132--136",
ISBN = "979-8-89176-265-7",
abstract = "As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided documents rather than relying on the model{'}s parametric knowledge, ensuring the trustworthiness and interpretability of these systems has become a critical concern. A central approach to addressing this challenge is \textbf{attribution}, which involves tracing the generated outputs back to their source documents. However, since LLMs can produce inaccurate or imprecise responses, it is crucial to assess the reliability of these citations.To tackle this, our work proposes two techniques. (1) A \textbf{zero-shot} approach that frames attribution as a straightforward textual entailment task. Our method using flan-ul2 demonstrates an improvement of 0.27{\%} and 2.4{\%} over the best baseline of ID and OOD sets of AttributionBench (CITATION), respectively. (2) We also explore the role of the \textbf{attention mechanism} in enhancing the attribution process. Using a smaller LLM, flan-t5-small, the F1 scores outperform the baseline across almost all layers except layer 4 and layers 8 through 11."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rawte-etal-2025-document">
<titleInfo>
<title>Document Attribution: Examining Citation Relationships using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vipula</namePart>
<namePart type="family">Rawte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedim</namePart>
<namePart type="family">Lipka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">De Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-265-7</identifier>
</relatedItem>
<abstract>As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided documents rather than relying on the model’s parametric knowledge, ensuring the trustworthiness and interpretability of these systems has become a critical concern. A central approach to addressing this challenge is attribution, which involves tracing the generated outputs back to their source documents. However, since LLMs can produce inaccurate or imprecise responses, it is crucial to assess the reliability of these citations.To tackle this, our work proposes two techniques. (1) A zero-shot approach that frames attribution as a straightforward textual entailment task. Our method using flan-ul2 demonstrates an improvement of 0.27% and 2.4% over the best baseline of ID and OOD sets of AttributionBench (CITATION), respectively. (2) We also explore the role of the attention mechanism in enhancing the attribution process. Using a smaller LLM, flan-t5-small, the F1 scores outperform the baseline across almost all layers except layer 4 and layers 8 through 11.</abstract>
<identifier type="citekey">rawte-etal-2025-document</identifier>
<identifier type="doi">10.18653/v1/2025.sdp-1.12</identifier>
<location>
<url>https://aclanthology.org/2025.sdp-1.12/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>132</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Attribution: Examining Citation Relationships using Large Language Models
%A Rawte, Vipula
%A Rossi, Ryan A.
%A Dernoncourt, Franck
%A Lipka, Nedim
%Y Ghosal, Tirthankar
%Y Mayr, Philipp
%Y Singh, Amanpreet
%Y Naik, Aakanksha
%Y Rehm, Georg
%Y Freitag, Dayne
%Y Li, Dan
%Y Schimmler, Sonja
%Y De Waard, Anita
%S Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-265-7
%F rawte-etal-2025-document
%X As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided documents rather than relying on the model’s parametric knowledge, ensuring the trustworthiness and interpretability of these systems has become a critical concern. A central approach to addressing this challenge is attribution, which involves tracing the generated outputs back to their source documents. However, since LLMs can produce inaccurate or imprecise responses, it is crucial to assess the reliability of these citations.To tackle this, our work proposes two techniques. (1) A zero-shot approach that frames attribution as a straightforward textual entailment task. Our method using flan-ul2 demonstrates an improvement of 0.27% and 2.4% over the best baseline of ID and OOD sets of AttributionBench (CITATION), respectively. (2) We also explore the role of the attention mechanism in enhancing the attribution process. Using a smaller LLM, flan-t5-small, the F1 scores outperform the baseline across almost all layers except layer 4 and layers 8 through 11.
%R 10.18653/v1/2025.sdp-1.12
%U https://aclanthology.org/2025.sdp-1.12/
%U https://doi.org/10.18653/v1/2025.sdp-1.12
%P 132-136
Markdown (Informal)
[Document Attribution: Examining Citation Relationships using Large Language Models](https://aclanthology.org/2025.sdp-1.12/) (Rawte et al., sdp 2025)
ACL