@inproceedings{kumar-etal-2026-beyond,
title = "Beyond Visual Similarity: Parameter-Efficient Vision{--}Language Models for Scientific Citation Linking on {A}stro{CLIMB}",
author = "Kumar, Ashmani and
Sharma, Shubham and
Ramalakshmi, K S and
Chopra, Ankush",
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-1.23/",
pages = "210--215",
ISBN = "979-8-89176-456-9",
abstract = "This paper describes our submission to the AstroCLIMB shared task, which evaluates whether multimodal models can identify citation relationships among astronomy papers from pairs of figures and captions. We explore an empirical progression spanning frozen embedding baselines, dual encoders, cross-encoders, and generative vision{--}language models (VLMs) adapted via parameter-efficient fine-tuning (LoRA with 4-bit quantization). Among our evaluated configurations, a fine-tuned Qwen3.8-27B achieves a test Macro-F1 of approximately 0.74. An auxiliary specialist adapter trained to re-rank the frequently confused \textit{same paper} and \textit{related papers} classes yields comparable performance within expected run-to-run variance. Across input modalities, Text{--}Text pairs achieve the highest classification accuracy, followed by Text{--}Figure pairs, while Figure{--}Figure pairs prove the most challenging. These findings demonstrate that visual similarity alone remains an insufficient proxy for semantic citation linkage in specialized scientific literature."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2026-beyond">
<titleInfo>
<title>Beyond Visual Similarity: Parameter-Efficient Vision–Language Models for Scientific Citation Linking on AstroCLIMB</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashmani</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Ramalakshmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankush</namePart>
<namePart type="family">Chopra</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>This paper describes our submission to the AstroCLIMB shared task, which evaluates whether multimodal models can identify citation relationships among astronomy papers from pairs of figures and captions. We explore an empirical progression spanning frozen embedding baselines, dual encoders, cross-encoders, and generative vision–language models (VLMs) adapted via parameter-efficient fine-tuning (LoRA with 4-bit quantization). Among our evaluated configurations, a fine-tuned Qwen3.8-27B achieves a test Macro-F1 of approximately 0.74. An auxiliary specialist adapter trained to re-rank the frequently confused same paper and related papers classes yields comparable performance within expected run-to-run variance. Across input modalities, Text–Text pairs achieve the highest classification accuracy, followed by Text–Figure pairs, while Figure–Figure pairs prove the most challenging. These findings demonstrate that visual similarity alone remains an insufficient proxy for semantic citation linkage in specialized scientific literature.</abstract>
<identifier type="citekey">kumar-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.23/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>210</start>
<end>215</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Visual Similarity: Parameter-Efficient Vision–Language Models for Scientific Citation Linking on AstroCLIMB
%A Kumar, Ashmani
%A Sharma, Shubham
%A Ramalakshmi, K. S.
%A Chopra, Ankush
%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 kumar-etal-2026-beyond
%X This paper describes our submission to the AstroCLIMB shared task, which evaluates whether multimodal models can identify citation relationships among astronomy papers from pairs of figures and captions. We explore an empirical progression spanning frozen embedding baselines, dual encoders, cross-encoders, and generative vision–language models (VLMs) adapted via parameter-efficient fine-tuning (LoRA with 4-bit quantization). Among our evaluated configurations, a fine-tuned Qwen3.8-27B achieves a test Macro-F1 of approximately 0.74. An auxiliary specialist adapter trained to re-rank the frequently confused same paper and related papers classes yields comparable performance within expected run-to-run variance. Across input modalities, Text–Text pairs achieve the highest classification accuracy, followed by Text–Figure pairs, while Figure–Figure pairs prove the most challenging. These findings demonstrate that visual similarity alone remains an insufficient proxy for semantic citation linkage in specialized scientific literature.
%U https://aclanthology.org/2026.wasp-1.23/
%P 210-215
Markdown (Informal)
[Beyond Visual Similarity: Parameter-Efficient Vision–Language Models for Scientific Citation Linking on AstroCLIMB](https://aclanthology.org/2026.wasp-1.23/) (Kumar et al., WASP 2026)
ACL