Intent-aware Schema Generation and Refinement for Literature Review Tables
TLDRThis work presents an approach for augmenting unannotated table corpora withSynthesized intents, and applies it to create a dataset for studying schema generation conditioned on a given information need, thus reducing ambiguity and comprehensively benchmarking several single-shot schema generation methods.
How do people cite this paper?
(generated 20 days ago)This paper has been cited as an example of LLM-driven approaches for detecting and structuring themes across large bodies of academic publications, situating it within a growing line of research on using language models to support qualitative analysis in literature reviews.