Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rocha, Victor Hugo Nascimento, Silveira, Igor Cataneo, Pirozelli, Paulo, Mauá, Denis Deratani, Cozman, Fabio Gagliardi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911928775868416
author Rocha, Victor Hugo Nascimento
Silveira, Igor Cataneo
Pirozelli, Paulo
Mauá, Denis Deratani
Cozman, Fabio Gagliardi
author_facet Rocha, Victor Hugo Nascimento
Silveira, Igor Cataneo
Pirozelli, Paulo
Mauá, Denis Deratani
Cozman, Fabio Gagliardi
contents The recent success of Large Language Models (LLMs) has sparked concerns about their potential to spread misinformation. As a result, there is a pressing need for tools to identify ``fake arguments'' generated by such models. To create these tools, examples of texts generated by LLMs are needed. This paper introduces a methodology to obtain good, bad and ugly arguments from argumentative essays produced by ChatGPT, OpenAI's LLM. We then describe a novel dataset containing a set of diverse arguments, ArGPT. We assess the effectiveness of our dataset and establish baselines for several argumentation-related tasks. Finally, we show that the artificially generated data relates well to human argumentation and thus is useful as a tool to train and test systems for the defined tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15130
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks
Rocha, Victor Hugo Nascimento
Silveira, Igor Cataneo
Pirozelli, Paulo
Mauá, Denis Deratani
Cozman, Fabio Gagliardi
Computation and Language
Artificial Intelligence
The recent success of Large Language Models (LLMs) has sparked concerns about their potential to spread misinformation. As a result, there is a pressing need for tools to identify ``fake arguments'' generated by such models. To create these tools, examples of texts generated by LLMs are needed. This paper introduces a methodology to obtain good, bad and ugly arguments from argumentative essays produced by ChatGPT, OpenAI's LLM. We then describe a novel dataset containing a set of diverse arguments, ArGPT. We assess the effectiveness of our dataset and establish baselines for several argumentation-related tasks. Finally, we show that the artificially generated data relates well to human argumentation and thus is useful as a tool to train and test systems for the defined tasks.
title Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.15130