DOLOMITES: Domain-Specific Long-Form Methodical Tasks
This addresses the need for automated assistance in pervasive expert writing tasks, but it is incremental as it primarily provides a new benchmark rather than a solution.
The paper tackled the problem of automating methodical long-form writing tasks in various expert domains by introducing DoLoMiTes, a benchmark with 519 tasks and 1,857 examples, and found that contemporary language models struggle with these complex generation challenges.
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.