@inproceedings{ghimire-etal-2026-psgs,
title = "{PSGS}@2026: From Figures to Citation Graphs: {QL}o{RA} Based Multimodal Linking for {A}stro{CLIMB}",
author = "Ghimire, Prajwal and
Saud, Shiv Ram and
Mahato, Aashish and
Dawadi, Sundeep and
Saud, Ramesh and
Regmi, Sunil and
Shakya, Manoj",
editor = "Accomazzi, Alberto and
Ghosal, Tirthankar and
Grezes, Felix and
Lockhart, Kelly and
Alkan, Atilla Kaan",
booktitle = "Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wasp-1.21/",
pages = "192--198",
ISBN = "979-8-89176-456-9",
abstract = "We describe our system for the AstroCLIMB shared task (WASP 2026), which reconstructs the citation graph of astronomy papers from scientific figures and captions alone. The task requires identifying the relationship between pairs of figures and captions as \texttt{same{\_}figure}, \texttt{same{\_}paper}, \texttt{related{\_}papers}, or \texttt{unrelated{\_}papers}. Our system finetunes \texttt{google/gemma-4-E4B-it} using QLoRA on 8,200 competition training rows with a shared descriptive prompt and greedy decoding. A zero shot baseline achieves 0.4408 macro F1 on a balanced 1,800 pair validation split held out from the competition training file, and the finetuned system substantially improves this citation-relation classification for the challenging \texttt{related{\_}papers} class in particular. Our submitted system achieves 0.64282 F1 on all 10,000 official test pairs. These results show that multimodal finetuning can improve citation-relation inference from scientific figures and captions when document metadata is unavailable."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghimire-etal-2026-psgs">
<titleInfo>
<title>PSGS@2026: From Figures to Citation Graphs: QLoRA Based Multimodal Linking for AstroCLIMB</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prajwal</namePart>
<namePart type="family">Ghimire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiv</namePart>
<namePart type="given">Ram</namePart>
<namePart type="family">Saud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aashish</namePart>
<namePart type="family">Mahato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sundeep</namePart>
<namePart type="family">Dawadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramesh</namePart>
<namePart type="family">Saud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="family">Shakya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Lockhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atilla</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Alkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-456-9</identifier>
</relatedItem>
<abstract>We describe our system for the AstroCLIMB shared task (WASP 2026), which reconstructs the citation graph of astronomy papers from scientific figures and captions alone. The task requires identifying the relationship between pairs of figures and captions as same_figure, same_paper, related_papers, or unrelated_papers. Our system finetunes google/gemma-4-E4B-it using QLoRA on 8,200 competition training rows with a shared descriptive prompt and greedy decoding. A zero shot baseline achieves 0.4408 macro F1 on a balanced 1,800 pair validation split held out from the competition training file, and the finetuned system substantially improves this citation-relation classification for the challenging related_papers class in particular. Our submitted system achieves 0.64282 F1 on all 10,000 official test pairs. These results show that multimodal finetuning can improve citation-relation inference from scientific figures and captions when document metadata is unavailable.</abstract>
<identifier type="citekey">ghimire-etal-2026-psgs</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.21/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>192</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PSGS@2026: From Figures to Citation Graphs: QLoRA Based Multimodal Linking for AstroCLIMB
%A Ghimire, Prajwal
%A Saud, Shiv Ram
%A Mahato, Aashish
%A Dawadi, Sundeep
%A Saud, Ramesh
%A Regmi, Sunil
%A Shakya, Manoj
%Y Accomazzi, Alberto
%Y Ghosal, Tirthankar
%Y Grezes, Felix
%Y Lockhart, Kelly
%Y Alkan, Atilla Kaan
%S Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-456-9
%F ghimire-etal-2026-psgs
%X We describe our system for the AstroCLIMB shared task (WASP 2026), which reconstructs the citation graph of astronomy papers from scientific figures and captions alone. The task requires identifying the relationship between pairs of figures and captions as same_figure, same_paper, related_papers, or unrelated_papers. Our system finetunes google/gemma-4-E4B-it using QLoRA on 8,200 competition training rows with a shared descriptive prompt and greedy decoding. A zero shot baseline achieves 0.4408 macro F1 on a balanced 1,800 pair validation split held out from the competition training file, and the finetuned system substantially improves this citation-relation classification for the challenging related_papers class in particular. Our submitted system achieves 0.64282 F1 on all 10,000 official test pairs. These results show that multimodal finetuning can improve citation-relation inference from scientific figures and captions when document metadata is unavailable.
%U https://aclanthology.org/2026.wasp-1.21/
%P 192-198
Markdown (Informal)
[PSGS@2026: From Figures to Citation Graphs: QLoRA Based Multimodal Linking for AstroCLIMB](https://aclanthology.org/2026.wasp-1.21/) (Ghimire et al., WASP 2026)
ACL
- Prajwal Ghimire, Shiv Ram Saud, Aashish Mahato, Sundeep Dawadi, Ramesh Saud, Sunil Regmi, and Manoj Shakya. 2026. PSGS@2026: From Figures to Citation Graphs: QLoRA Based Multimodal Linking for AstroCLIMB. In Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications, pages 192–198, Hengqin, Zhuhai, China. Association for Computational Linguistics.