We also find that providing more table context (captions, in-text references) to models leads to higher recall when generating columns but does not help when generating values.

We find that using decontextualization with SBERT leads to a better evaluator than Llama 3, which hallucinates alignments.

We propose a two-step procedure for generating tables given the input papers:
1️⃣ Generate the schemas (sets of columns)
2️⃣ Fill in the values.

This table generation task takes as input multiple papers, and synthesizes them into a single output table. We collect a dataset of such tables and associated papers, and augment the tables with additional context such as their captions and in-text references.

✨EMNLP Paper! ✨
Have you ever constructed a table to organize your literature review process? Can we use LMs to generate these automatically?

We are excited to present ArxivDIGESTables 🍽️ a study of collecting, generating, and evaluating 🎓 scientific literature review tables 📃!