# Question Answering with Texts and Tables through Deep Reinforcement Learning

Source: [Question Answering with Texts and Tables through Deep Reinforcement Learning](<https://www.sota2.com/research/paper/68fa77101e209131cea70e24>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:08:58.245Z

Authors: Marcos M. Jos\\'e, Fl\\'avio N. Ca\\c{c}\\~ao, Maria F. Ribeiro, Rafael M. Cheang, Paulo Pirozelli, Fabio G. Cozman

Published: 2024-07-05T20:44:01.000Z

## Abstract

This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Question Answering dataset for validation and training. One of the most common ways to generate answers in this setting is to retrieve information sequentially, where a selected piece of data helps searching for the next piece. As different models can have distinct behaviors when called in this sequential information search, a challenge is how to select models at each step. Our architecture employs reinforcement learning to choose between different state-of-the-art tools sequentially until, in the end, a desired answer is generated. This system achieved an F1-score of 19.03, comparable to iterative systems in the literature.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.04858>)

[PDF](<https://arxiv.org/pdf/2407.04858.pdf>)