Can formal argumentative reasoning enhance LLMs performances?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Castagna, Federico, Sassoon, Isabel, Parsons, Simon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929352109719552
author Castagna, Federico
Sassoon, Isabel
Parsons, Simon
author_facet Castagna, Federico
Sassoon, Isabel
Parsons, Simon
contents Recent years witnessed significant performance advancements in deep-learning-driven natural language models, with a strong focus on the development and release of Large Language Models (LLMs). These improvements resulted in better quality AI-generated output but rely on resource-expensive training and upgrading of models. Although different studies have proposed a range of techniques to enhance LLMs without retraining, none have considered computational argumentation as an option. This is a missed opportunity since computational argumentation is an intuitive mechanism that formally captures agents' interactions and the information conflict that may arise during such interplays, and so it seems well-suited for boosting the reasoning and conversational abilities of LLMs in a seamless manner. In this paper, we present a pipeline (MQArgEng) and preliminary study to evaluate the effect of introducing computational argumentation semantics on the performance of LLMs. Our experiment's goal was to provide a proof-of-concept and a feasibility analysis in order to foster (or deter) future research towards a fully-fledged argumentation engine plugin for LLMs. Exploratory results using the MT-Bench indicate that MQArgEng provides a moderate performance gain in most of the examined topical categories and, as such, show promise and warrant further research.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13036
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can formal argumentative reasoning enhance LLMs performances?
Castagna, Federico
Sassoon, Isabel
Parsons, Simon
Computation and Language
Artificial Intelligence
Recent years witnessed significant performance advancements in deep-learning-driven natural language models, with a strong focus on the development and release of Large Language Models (LLMs). These improvements resulted in better quality AI-generated output but rely on resource-expensive training and upgrading of models. Although different studies have proposed a range of techniques to enhance LLMs without retraining, none have considered computational argumentation as an option. This is a missed opportunity since computational argumentation is an intuitive mechanism that formally captures agents' interactions and the information conflict that may arise during such interplays, and so it seems well-suited for boosting the reasoning and conversational abilities of LLMs in a seamless manner. In this paper, we present a pipeline (MQArgEng) and preliminary study to evaluate the effect of introducing computational argumentation semantics on the performance of LLMs. Our experiment's goal was to provide a proof-of-concept and a feasibility analysis in order to foster (or deter) future research towards a fully-fledged argumentation engine plugin for LLMs. Exploratory results using the MT-Bench indicate that MQArgEng provides a moderate performance gain in most of the examined topical categories and, as such, show promise and warrant further research.
title Can formal argumentative reasoning enhance LLMs performances?
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.13036