ReAcTable: Enhancing ReAct for Table Question Answering
Yunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon, Shaleen, Deep, Jignesh M. Patel

TL;DR
ReAcTable is a novel framework that enhances the ReAct paradigm for table question answering by integrating external tools like SQL and Python to improve reasoning and data transformation, achieving state-of-the-art results.
Contribution
It introduces ReAcTable, a new approach that combines incremental reasoning with external tools for improved TQA performance without fine-tuning.
Findings
Outperforms previous methods on WikiTQ benchmark with 68.0% accuracy.
Effectively handles complex data semantics and errors in tabular data.
Enhances reasoning capabilities by integrating external code execution tools.
Abstract
Table Question Answering (TQA) presents a substantial challenge at the intersection of natural language processing and data analytics. This task involves answering natural language (NL) questions on top of tabular data, demanding proficiency in logical reasoning, understanding of data semantics, and fundamental analytical capabilities. Due to its significance, a substantial volume of research has been dedicated to exploring a wide range of strategies aimed at tackling this challenge including approaches that leverage Large Language Models (LLMs) through in-context learning or Chain-of-Thought (CoT) prompting as well as approaches that train and fine-tune custom models. Nonetheless, a conspicuous gap exists in the research landscape, where there is limited exploration of how innovative foundational research, which integrates incremental reasoning with external tools in the context of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Data Quality and Management
