@article{malaviya-etal-2025-dolomites,
title = "Dolomites: Domain-Specific Long-Form Methodical Tasks",
author = "Malaviya, Chaitanya and
Agrawal, Priyanka and
Ganchev, Kuzman and
Srinivasan, Pranesh and
Huot, Fantine and
Berant, Jonathan and
Yatskar, Mark and
Das, Dipanjan and
Lapata, Mirella and
Alberti, Chris",
journal = "Transactions of the Association for Computational Linguistics",
volume = "13",
year = "2025",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2025.tacl-1.1/",
doi = "10.1162/tacl_a_00727",
pages = "1--29",
abstract = "Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models, highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge. Our dataset is available at https://dolomites-benchmark.github.io/."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malaviya-etal-2025-dolomites">
<titleInfo>
<title>Dolomites: Domain-Specific Long-Form Methodical Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Malaviya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuzman</namePart>
<namePart type="family">Ganchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranesh</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fantine</namePart>
<namePart type="family">Huot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Yatskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Alberti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models, highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge. Our dataset is available at https://dolomites-benchmark.github.io/.</abstract>
<identifier type="citekey">malaviya-etal-2025-dolomites</identifier>
<identifier type="doi">10.1162/tacl_a_00727</identifier>
<location>
<url>https://aclanthology.org/2025.tacl-1.1/</url>
</location>
<part>
<date>2025</date>
<detail type="volume"><number>13</number></detail>
<extent unit="page">
<start>1</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Dolomites: Domain-Specific Long-Form Methodical Tasks
%A Malaviya, Chaitanya
%A Agrawal, Priyanka
%A Ganchev, Kuzman
%A Srinivasan, Pranesh
%A Huot, Fantine
%A Berant, Jonathan
%A Yatskar, Mark
%A Das, Dipanjan
%A Lapata, Mirella
%A Alberti, Chris
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F malaviya-etal-2025-dolomites
%X Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models, highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge. Our dataset is available at https://dolomites-benchmark.github.io/.
%R 10.1162/tacl_a_00727
%U https://aclanthology.org/2025.tacl-1.1/
%U https://doi.org/10.1162/tacl_a_00727
%P 1-29
Markdown (Informal)
[Dolomites: Domain-Specific Long-Form Methodical Tasks](https://aclanthology.org/2025.tacl-1.1/) (Malaviya et al., TACL 2025)
ACL
- Chaitanya Malaviya, Priyanka Agrawal, Kuzman Ganchev, Pranesh Srinivasan, Fantine Huot, Jonathan Berant, Mark Yatskar, Dipanjan Das, Mirella Lapata, and Chris Alberti. 2025. Dolomites: Domain-Specific Long-Form Methodical Tasks. Transactions of the Association for Computational Linguistics, 13:1–29.