@inproceedings{wang-etal-2026-scalar,
title = "{SCALAR}: Scientific Citation-based Live Assessment of Long-context Academic Reasoning",
author = "Wang, Renxi and
Mu, Honglin and
Ma, Liqun and
Lin, Lizhi and
Feng, Yunlong and
Baldwin, Timothy and
Han, Xudong and
Li, Haonan",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.366/",
pages = "7817--7830",
ISBN = "979-8-89176-380-7",
abstract = "Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchmark designed to assess citation-grounded long-context reasoning in academic writing. SCALAR leverages academic papers and their citation structure to automatically generate high-quality ground-truth labels without human annotation. It features controllable difficulty levels and a dynamic updating mechanism that mitigates data contamination. The benchmark includes two tasks: a multiple-choice QA format and a cloze-style citation prediction. We evaluate a range of state-of-the-art LLMs and find that the multiple-choice task effectively distinguishes model capabilities{---}while human experts achieve over 90{\%} accuracy, most models struggle. The cloze-style task is even more challenging, with no model exceeding 40{\%} accuracy. SCALAR provides a domain-grounded, continuously updating framework for tracking progress in citation-based long-context understanding. Code and data will be publicly released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-scalar">
<titleInfo>
<title>SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renxi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Honglin</namePart>
<namePart type="family">Mu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunlong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haonan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchmark designed to assess citation-grounded long-context reasoning in academic writing. SCALAR leverages academic papers and their citation structure to automatically generate high-quality ground-truth labels without human annotation. It features controllable difficulty levels and a dynamic updating mechanism that mitigates data contamination. The benchmark includes two tasks: a multiple-choice QA format and a cloze-style citation prediction. We evaluate a range of state-of-the-art LLMs and find that the multiple-choice task effectively distinguishes model capabilities—while human experts achieve over 90% accuracy, most models struggle. The cloze-style task is even more challenging, with no model exceeding 40% accuracy. SCALAR provides a domain-grounded, continuously updating framework for tracking progress in citation-based long-context understanding. Code and data will be publicly released.</abstract>
<identifier type="citekey">wang-etal-2026-scalar</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.366/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>7817</start>
<end>7830</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning
%A Wang, Renxi
%A Mu, Honglin
%A Ma, Liqun
%A Lin, Lizhi
%A Feng, Yunlong
%A Baldwin, Timothy
%A Han, Xudong
%A Li, Haonan
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F wang-etal-2026-scalar
%X Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchmark designed to assess citation-grounded long-context reasoning in academic writing. SCALAR leverages academic papers and their citation structure to automatically generate high-quality ground-truth labels without human annotation. It features controllable difficulty levels and a dynamic updating mechanism that mitigates data contamination. The benchmark includes two tasks: a multiple-choice QA format and a cloze-style citation prediction. We evaluate a range of state-of-the-art LLMs and find that the multiple-choice task effectively distinguishes model capabilities—while human experts achieve over 90% accuracy, most models struggle. The cloze-style task is even more challenging, with no model exceeding 40% accuracy. SCALAR provides a domain-grounded, continuously updating framework for tracking progress in citation-based long-context understanding. Code and data will be publicly released.
%U https://aclanthology.org/2026.eacl-long.366/
%P 7817-7830
Markdown (Informal)
[SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning](https://aclanthology.org/2026.eacl-long.366/) (Wang et al., EACL 2026)
ACL
- Renxi Wang, Honglin Mu, Liqun Ma, Lizhi Lin, Yunlong Feng, Timothy Baldwin, Xudong Han, and Haonan Li. 2026. SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7817–7830, Rabat, Morocco. Association for Computational Linguistics.