Summary of Docfinqa: a Long-context Financial Reasoning Dataset, by Varshini Reddy et al.
DocFinQA: A Long-Context Financial Reasoning Dataset
by Varshini Reddy, Rik Koncel-Kedziorski, Viet Dac Lai, Michael Krumdick, Charles Lovering, Chris Tanner
First submitted to arxiv on: 12 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a new financial question-answering (QA) task that tackles the challenge of working with lengthy documents common in the financial domain. By augmenting existing FinQA data with full-document context, the authors create DocFinQA, a dataset featuring 7,437 questions and an average context length of 123k words. The paper explores the performance of state-of-the-art systems on this new task, highlighting the difficulties even top-performing models face when dealing with the longest documents in DocFinQA. This work has far-reaching implications for applications like gene sequences and legal document contract analysis. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at answering questions about long financial documents. Right now, most computer systems can only handle short pieces of these documents, but real-world professionals often deal with hundreds of pages. To make things more realistic, the researchers created a new dataset called DocFinQA that includes full documents and 7,437 questions. They tested how well state-of-the-art computers perform on this task and found that even the best ones struggle with the longest documents. |
Keywords
» Artificial intelligence » Context length » Question answering
