@inproceedings{hamdi-etal-2026-narrator,
title = "{NARRATOR}: Narrative-Aware Routing and Evaluation of Large Language Models",
author = "Hamdi, Ahmed and
Moreno, Jose G and
Doucet, Antoine and
Gonz{\'a}lez, Fabio A.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1899/",
pages = "43288--43303",
ISBN = "979-8-89176-459-0",
abstract = "Narrative NLP encompasses a diverse set of competencies such as detecting whether a text contains a narrative, classifying its genre or function, completing its plot, and judging similarity between stories. However, the relationship between model capabilities across these sub-tasks remains poorly understood and no unified benchmark exists to evaluate large language models across these dimensions simultaneously. In this paper, we introduce NARRATOR, a unified benchmark of 96,818 multiple-choice questions derived from six narrative datasets spanning detection, classification, story completion, and similarity. Evaluating 50 open-weight LLMs in a zero-shot setting reveals that LLM performance profiles are highly heterogeneous and no model dominates across all sub-tasks. To exploit this complementarity efficiently, we learn compact narrative competence embeddings of LLMs using a matrix factorisation over a binary correctness matrix, without accessing model weights. A single linear layer on top of these frozen embeddings supports model routing (71.1{\%}), correctness forecasting (65.3{\%}), and benchmark accuracy prediction (mean Kendall{'}s $\tau = 0.72$) at near-zero inference cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamdi-etal-2026-narrator">
<titleInfo>
<title>NARRATOR: Narrative-Aware Routing and Evaluation of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Doucet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">A</namePart>
<namePart type="family">González</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Narrative NLP encompasses a diverse set of competencies such as detecting whether a text contains a narrative, classifying its genre or function, completing its plot, and judging similarity between stories. However, the relationship between model capabilities across these sub-tasks remains poorly understood and no unified benchmark exists to evaluate large language models across these dimensions simultaneously. In this paper, we introduce NARRATOR, a unified benchmark of 96,818 multiple-choice questions derived from six narrative datasets spanning detection, classification, story completion, and similarity. Evaluating 50 open-weight LLMs in a zero-shot setting reveals that LLM performance profiles are highly heterogeneous and no model dominates across all sub-tasks. To exploit this complementarity efficiently, we learn compact narrative competence embeddings of LLMs using a matrix factorisation over a binary correctness matrix, without accessing model weights. A single linear layer on top of these frozen embeddings supports model routing (71.1%), correctness forecasting (65.3%), and benchmark accuracy prediction (mean Kendall’s τ = 0.72) at near-zero inference cost.</abstract>
<identifier type="citekey">hamdi-etal-2026-narrator</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1899/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43288</start>
<end>43303</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NARRATOR: Narrative-Aware Routing and Evaluation of Large Language Models
%A Hamdi, Ahmed
%A Moreno, Jose G.
%A Doucet, Antoine
%A González, Fabio A.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F hamdi-etal-2026-narrator
%X Narrative NLP encompasses a diverse set of competencies such as detecting whether a text contains a narrative, classifying its genre or function, completing its plot, and judging similarity between stories. However, the relationship between model capabilities across these sub-tasks remains poorly understood and no unified benchmark exists to evaluate large language models across these dimensions simultaneously. In this paper, we introduce NARRATOR, a unified benchmark of 96,818 multiple-choice questions derived from six narrative datasets spanning detection, classification, story completion, and similarity. Evaluating 50 open-weight LLMs in a zero-shot setting reveals that LLM performance profiles are highly heterogeneous and no model dominates across all sub-tasks. To exploit this complementarity efficiently, we learn compact narrative competence embeddings of LLMs using a matrix factorisation over a binary correctness matrix, without accessing model weights. A single linear layer on top of these frozen embeddings supports model routing (71.1%), correctness forecasting (65.3%), and benchmark accuracy prediction (mean Kendall’s τ = 0.72) at near-zero inference cost.
%U https://aclanthology.org/2026.emnlp-main.1899/
%P 43288-43303
Markdown (Informal)
[NARRATOR: Narrative-Aware Routing and Evaluation of Large Language Models](https://aclanthology.org/2026.emnlp-main.1899/) (Hamdi et al., EMNLP 2026)
ACL