Assisted Debate Builder with Large Language Models

TL;DR

ADBL2 is an open-source tool that uses large language models for relation-based argument mining, enabling verification and creation of debate arguments across domains, with a fine-tuned model achieving high accuracy.

Contribution

It introduces the first open-source relation-based argument mining tool that leverages large language models and provides a fine-tuned LLM outperforming existing methods.

Findings

Achieved an F1-score of 90.59% in relation-based argument mining.

Demonstrated modularity with compatibility across open-source LLMs.

First to fine-tune Mistral-7B for argument mining tasks.

Abstract

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.