# Reversing The Twenty Questions Game

Source: [Reversing The Twenty Questions Game](<https://www.sota2.com/research/paper/68fa6e661e209131cea3fbe7>)

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

Data updated: 2025-10-26T00:56:59.119Z

Authors: Parth Parikh, Anisha Gupta

Published: 2023-01-19T12:51:59.000Z

## Abstract

Twenty questions is a widely popular verbal game. In recent years, many computerized versions of this game have been developed in which a user thinks of an entity and a computer attempts to guess this entity by asking a series of boolean-type (yes/no) questions. In this research, we aim to reverse this game by making the computer choose an entity at random. The human aims to guess this entity by quizzing the computer with natural language queries which the computer will then attempt to parse using a boolean question answering model. The game ends when the human is successfully able to guess the entity of the computer's choice.

## 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/2301.08718>)

[PDF](<https://arxiv.org/pdf/2301.08718.pdf>)
