@inproceedings{bexte-etal-2026-picturestories,
title = "{P}icture{S}tories: Predicting the Task Adherence of Language Learner Answers to a Picture Story-Based Writing Task",
author = "Bexte, Marie and
Caines, Andrew and
Nicholls, Diane and
Buttery, Paula and
Zesch, Torsten",
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.108/",
pages = "2398--2415",
ISBN = "979-8-89176-380-7",
abstract = "We investigate the automated evaluation of English language learner answers to writing tasks featuring picture stories.This is usually limited to language proficiency only, neglecting the context of the picture. Instead, our analysis focuses on task adherence, which for example allows detection of off-topic answers.Since there is a lack of suitable training and evaluation data, our first step is to build the PictureStories dataset.To this end, we develop a marking rubric that covers task adherence with respect to both form and content. Six annotators mark 713 learner answers written in response to one of five picture stories.Having assembled the dataset, we then explore to what extent task adherence can be predicted automatically. Our experiments assume a scenario where no or just a few labelled answers are available for the picture story which is being marked.For form-focused criteria, we find that it is beneficial to finetune models across tasks.With content-focused criteria, few-shot prompting Qwen emerges as the best-performing method. We examine the trade-off between including the story image vs. example answers in the prompt and find that examples suffice in many cases. While for some LLMs, few-shot prompting results may look promising on the surface, we demonstrate that a much simpler method can do just as well when shown the same examples."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bexte-etal-2026-picturestories">
<titleInfo>
<title>PictureStories: Predicting the Task Adherence of Language Learner Answers to a Picture Story-Based Writing Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Nicholls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</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>We investigate the automated evaluation of English language learner answers to writing tasks featuring picture stories.This is usually limited to language proficiency only, neglecting the context of the picture. Instead, our analysis focuses on task adherence, which for example allows detection of off-topic answers.Since there is a lack of suitable training and evaluation data, our first step is to build the PictureStories dataset.To this end, we develop a marking rubric that covers task adherence with respect to both form and content. Six annotators mark 713 learner answers written in response to one of five picture stories.Having assembled the dataset, we then explore to what extent task adherence can be predicted automatically. Our experiments assume a scenario where no or just a few labelled answers are available for the picture story which is being marked.For form-focused criteria, we find that it is beneficial to finetune models across tasks.With content-focused criteria, few-shot prompting Qwen emerges as the best-performing method. We examine the trade-off between including the story image vs. example answers in the prompt and find that examples suffice in many cases. While for some LLMs, few-shot prompting results may look promising on the surface, we demonstrate that a much simpler method can do just as well when shown the same examples.</abstract>
<identifier type="citekey">bexte-etal-2026-picturestories</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.108/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>2398</start>
<end>2415</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PictureStories: Predicting the Task Adherence of Language Learner Answers to a Picture Story-Based Writing Task
%A Bexte, Marie
%A Caines, Andrew
%A Nicholls, Diane
%A Buttery, Paula
%A Zesch, Torsten
%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 bexte-etal-2026-picturestories
%X We investigate the automated evaluation of English language learner answers to writing tasks featuring picture stories.This is usually limited to language proficiency only, neglecting the context of the picture. Instead, our analysis focuses on task adherence, which for example allows detection of off-topic answers.Since there is a lack of suitable training and evaluation data, our first step is to build the PictureStories dataset.To this end, we develop a marking rubric that covers task adherence with respect to both form and content. Six annotators mark 713 learner answers written in response to one of five picture stories.Having assembled the dataset, we then explore to what extent task adherence can be predicted automatically. Our experiments assume a scenario where no or just a few labelled answers are available for the picture story which is being marked.For form-focused criteria, we find that it is beneficial to finetune models across tasks.With content-focused criteria, few-shot prompting Qwen emerges as the best-performing method. We examine the trade-off between including the story image vs. example answers in the prompt and find that examples suffice in many cases. While for some LLMs, few-shot prompting results may look promising on the surface, we demonstrate that a much simpler method can do just as well when shown the same examples.
%U https://aclanthology.org/2026.eacl-long.108/
%P 2398-2415
Markdown (Informal)
[PictureStories: Predicting the Task Adherence of Language Learner Answers to a Picture Story-Based Writing Task](https://aclanthology.org/2026.eacl-long.108/) (Bexte et al., EACL 2026)
ACL