Assisted Debate Builder with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Faugier, Elliot, Armetta, Frédéric, Bonifati, Angela, Yun, Bruno
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917672593129472
author Faugier, Elliot
Armetta, Frédéric
Bonifati, Angela
Yun, Bruno
author_facet Faugier, Elliot
Armetta, Frédéric
Bonifati, Angela
Yun, Bruno
contents We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that leverages relation-based mining for (1) the verification of pre-established relations in a debate and (2) the assisted creation of new arguments by means of large language models. ADBL2 is highly modular and can work with any open-source large language models that are used as plugins. As a by-product, we also provide the first fine-tuned Mistral-7B large language model for relation-based argument mining, usable by ADBL2, which outperforms existing approaches for this task with an overall F1-score of 90.59% across all domains.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13015
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Assisted Debate Builder with Large Language Models
Faugier, Elliot
Armetta, Frédéric
Bonifati, Angela
Yun, Bruno
Computation and Language
Artificial Intelligence
We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that leverages relation-based mining for (1) the verification of pre-established relations in a debate and (2) the assisted creation of new arguments by means of large language models. ADBL2 is highly modular and can work with any open-source large language models that are used as plugins. As a by-product, we also provide the first fine-tuned Mistral-7B large language model for relation-based argument mining, usable by ADBL2, which outperforms existing approaches for this task with an overall F1-score of 90.59% across all domains.
title Assisted Debate Builder with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.13015