DOLOMITES: Domain-Specific Long-Form Methodical Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913555398262784 |
|---|---|
| author | Malaviya, Chaitanya Agrawal, Priyanka Ganchev, Kuzman Srinivasan, Pranesh Huot, Fantine Berant, Jonathan Yatskar, Mark Das, Dipanjan Lapata, Mirella Alberti, Chris |
| author_facet | Malaviya, Chaitanya Agrawal, Priyanka Ganchev, Kuzman Srinivasan, Pranesh Huot, Fantine Berant, Jonathan Yatskar, Mark Das, Dipanjan Lapata, Mirella Alberti, Chris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05938 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DOLOMITES: Domain-Specific Long-Form Methodical Tasks Malaviya, Chaitanya Agrawal, Priyanka Ganchev, Kuzman Srinivasan, Pranesh Huot, Fantine Berant, Jonathan Yatskar, Mark Das, Dipanjan Lapata, Mirella Alberti, Chris Computation and Language 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. |
| title | DOLOMITES: Domain-Specific Long-Form Methodical Tasks |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.05938 |