@inproceedings{al-laith-etal-2026-novelsum,
title = "{NOVELSUM}: Evaluating Long-Form Summary Generation for Historical {S}candinavian Novels",
author = "Al-Laith, Ali and
Conroy, Alexander and
Degn, Kirstine Nielsen and
Bjerring-Hansen, Jens and
Hershcovich, Daniel",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.780/",
doi = "10.63317/22upgvjw86b9",
pages = "9953--9963",
abstract = "We study long-form summarization of late-19th-century Danish and Norwegian novels and propose NOVELSUM, an evaluation resource and protocol tailored to literary narrative. We use a curated set of historical novels paired with professional reference summaries to establish baselines with long-document encoder{--}decoder models and prompt-based large-context LLMs. We evaluate with automatic metrics, expert human judgments, and LLM-as-judge scoring. Our human study identifies evaluation dimensions and literary facets that achieve substantial inter-annotator agreement and align with scholarly expectations. We further analyze reference-free evaluation, showing when it tracks expert trends and where it fails (notably for factual and setting-related criteria), thereby clarifying its utility when gold references or expert readers are unavailable. Our results benchmark long-context and prompted LLM approaches on historical literary prose and offer a practical path for human-grounded and reference-free assessment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-laith-etal-2026-novelsum">
<titleInfo>
<title>NOVELSUM: Evaluating Long-Form Summary Generation for Historical Scandinavian Novels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Laith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Conroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirstine</namePart>
<namePart type="given">Nielsen</namePart>
<namePart type="family">Degn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Bjerring-Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study long-form summarization of late-19th-century Danish and Norwegian novels and propose NOVELSUM, an evaluation resource and protocol tailored to literary narrative. We use a curated set of historical novels paired with professional reference summaries to establish baselines with long-document encoder–decoder models and prompt-based large-context LLMs. We evaluate with automatic metrics, expert human judgments, and LLM-as-judge scoring. Our human study identifies evaluation dimensions and literary facets that achieve substantial inter-annotator agreement and align with scholarly expectations. We further analyze reference-free evaluation, showing when it tracks expert trends and where it fails (notably for factual and setting-related criteria), thereby clarifying its utility when gold references or expert readers are unavailable. Our results benchmark long-context and prompted LLM approaches on historical literary prose and offer a practical path for human-grounded and reference-free assessment.</abstract>
<identifier type="citekey">al-laith-etal-2026-novelsum</identifier>
<identifier type="doi">10.63317/22upgvjw86b9</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.780/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9953</start>
<end>9963</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NOVELSUM: Evaluating Long-Form Summary Generation for Historical Scandinavian Novels
%A Al-Laith, Ali
%A Conroy, Alexander
%A Degn, Kirstine Nielsen
%A Bjerring-Hansen, Jens
%A Hershcovich, Daniel
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F al-laith-etal-2026-novelsum
%X We study long-form summarization of late-19th-century Danish and Norwegian novels and propose NOVELSUM, an evaluation resource and protocol tailored to literary narrative. We use a curated set of historical novels paired with professional reference summaries to establish baselines with long-document encoder–decoder models and prompt-based large-context LLMs. We evaluate with automatic metrics, expert human judgments, and LLM-as-judge scoring. Our human study identifies evaluation dimensions and literary facets that achieve substantial inter-annotator agreement and align with scholarly expectations. We further analyze reference-free evaluation, showing when it tracks expert trends and where it fails (notably for factual and setting-related criteria), thereby clarifying its utility when gold references or expert readers are unavailable. Our results benchmark long-context and prompted LLM approaches on historical literary prose and offer a practical path for human-grounded and reference-free assessment.
%R 10.63317/22upgvjw86b9
%U https://aclanthology.org/2026.lrec-1.780/
%U https://doi.org/10.63317/22upgvjw86b9
%P 9953-9963
Markdown (Informal)
[NOVELSUM: Evaluating Long-Form Summary Generation for Historical Scandinavian Novels](https://aclanthology.org/2026.lrec-1.780/) (Al-Laith et al., LREC 2026)
ACL