ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
TLDRA framework that leverages LMs to perform this task by decomposing it into separate schema and value generation steps is introduced, and it is found that even when LMs fail to fully reconstruct a reference table, their generated novel aspects can still be useful.
How do people cite this paper?
(generated 20 days ago)ArxivDIGESTables has been cited as a complete pipeline for decomposing literature review table generation into schema learning and value filling subtasks, referenced as a representative example of LLM-assisted literature reviewing, and its dataset and methods have been adopted for scientific domain NLP research and used as a benchmark for evaluating LLMs on structured generation tasks.