Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/29076
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Castagna, F | - |
dc.contributor.author | Sassoon, I | - |
dc.contributor.author | Parsons, S | - |
dc.date.accessioned | 2024-05-30T06:47:58Z | - |
dc.date.available | 2024-05-30T06:47:58Z | - |
dc.date.issued | 2024-05-16 | - |
dc.identifier | ORCiD: Federico Castagna https://orcid.org/0000-0002-5142-4386 | - |
dc.identifier | ORCiD: Isabel Sassoon https://orcid.org/0000-0002-8685-1054 | - |
dc.identifier | arXiv:2405.13036v1 [cs.CL] | - |
dc.identifier.citation | Castagna, F., Sassoon, I. and Parsons, S. (2024) 'Can formal argumentative reasoning enhance LLMs performances?', arXiv:2405.13036v1 [cs.CL] (preprint), pp. 1 - 7. doi: 10.48550/arXiv.2405.13036. | en_US |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/29076 | - |
dc.description.abstract | 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. | en_US |
dc.format.extent | 1 - 7 | - |
dc.format.medium | Electronic | - |
dc.language.iso | en_US | en_US |
dc.publisher | Cornell University | en_US |
dc.relation.uri | https://arxiv.org/abs/2405.13036v1 | - |
dc.rights | Copyright © 2024 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | computation and language (cs.CL) | en_US |
dc.subject | artificial intelligence (cs.AI) | en_US |
dc.title | Can formal argumentative reasoning enhance LLMs performances? | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.48550/arXiv.2405.13036 | - |
dc.identifier.eissn | 2331-8422 | - |
dc.rights.license | https://creativecommons.org/licenses/by/4.0/legalcode.en | - |
dc.rights.holder | The Author(s) | - |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Preprint.pdf | Copyright © 2024 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). | 472.78 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License