Skip to main content

Research Repository

Advanced Search

Dr Simon Wells' Outputs (29)

Formal Dialogue and Large Language Models (2024)
Presentation / Conference Contribution
Snaith, M., & Wells, S. (2024, October). Formal Dialogue and Large Language Models. Presented at SICSA Workshop on Reasoning, Evaluation and Application of Large Language Models (SICSA-REALLM 2024), Aberdeen, UK

In this paper, we present preliminary work into combining formal models of dialogue and large language models, before going on to discuss how this provides a foundation for similar approaches involving computational models of argument. First, we addr... Read More about Formal Dialogue and Large Language Models.

Thou Shalt Not Squander Life – Comparing Five Approaches to Argument Strength (2023)
Journal Article
Zenker, F., Dębowska-Kozłowska, K., Godden, D., Selinger, M., & Wells, S. (2023). Thou Shalt Not Squander Life – Comparing Five Approaches to Argument Strength. Studies in Logic, Grammar and Rhetoric, 68(1), 133-167. https://doi.org/10.2478/slgr-2023-0007

Different approaches analyze the strength of a natural language argument in different ways. This paper contrasts the dialectical, structural, probabilistic (or Bayesian), computational, and empirical approaches by exemplarily applying them to a singl... Read More about Thou Shalt Not Squander Life – Comparing Five Approaches to Argument Strength.

Reconsidering RepStat Rules in Dialectical Games (2022)
Presentation / Conference Contribution
Wells, S., & Snaith, M. (2022, September). Reconsidering RepStat Rules in Dialectical Games. Presented at 22nd Workshop on Computational Models of Natural Argument, Cardiff, Wales

Prohibition of repeated statements has benefits for the tractability and predictability of dialogues carried out by machines, but doesn’t match the real world behaviour of people. This gap between human and machine behaviour leads to problems when fo... Read More about Reconsidering RepStat Rules in Dialectical Games.

Burdens of Proposing: On the Burden of Proof in Deliberation Dialogues (2022)
Journal Article
Godden, D., & Wells, S. (2022). Burdens of Proposing: On the Burden of Proof in Deliberation Dialogues. Informal Logic, 42(1), 291-342. https://doi.org/10.22329/il.v42i1.7225

This paper considers the probative burdens of proposing action or policy options in deliberation dialogues. Do proposers bear a burden of proof? Building on pioneering work by Douglas Walton (2010), and following on a growing literature within comput... Read More about Burdens of Proposing: On the Burden of Proof in Deliberation Dialogues.

Towards a Declarative Approach to Constructing Dialogue Games (2021)
Presentation / Conference Contribution
Snaith, M., & Wells, S. (2021, September). Towards a Declarative Approach to Constructing Dialogue Games. Presented at CMNA’21: Workshop on Computational Models of Natural Argument, Online

In this paper we sketch a new approach to the development of dialogue games that builds upon the knowledge gained from several decades of dialogue game research across a variety of communities and which leverages the capabilities of the Dialogue Game... Read More about Towards a Declarative Approach to Constructing Dialogue Games.

Design and Evaluation of Visualisation Techniques to Facilitate Argument Exploration (2021)
Journal Article
Khartabil, D., Collins, C., Wells, S., Bach, B., & Kennedy, J. (2021). Design and Evaluation of Visualisation Techniques to Facilitate Argument Exploration. Computer Graphics Forum, 40(6), 447-465. https://doi.org/10.1111/cgf.14389

This paper reports the design and comparison of three visualizations to represent the structure and content within arguments. Arguments are artefacts of reasoning widely used across domains such as education, policy making, and science. An argument i... Read More about Design and Evaluation of Visualisation Techniques to Facilitate Argument Exploration.

Trusting Intelligent Machines: Deepening Trust Within Socio-Technical Systems (2018)
Journal Article
Andras, P., Esterle, L., Guckert, M., Anh Han, T., Lewis, P. R., Milanovic, K., Payne, T., Perret, C., Pitt, J., Powers, S. T., Urquhart, N., & Wells, S. (2018). Trusting Intelligent Machines: Deepening Trust Within Socio-Technical Systems. IEEE technology & society magazine, 37(4), 76-83. https://doi.org/10.1109/MTS.2018.2876107

Intelligent machines have reached capabilities that go beyond a level that a human being can fully comprehend without sufficiently detailed understanding of the underlying mechanisms. The choice of moves in the game Go (generated by Deep Mind?s Alpha... Read More about Trusting Intelligent Machines: Deepening Trust Within Socio-Technical Systems.

Information Diffusion in Multi-Agent Communities (2017)
Presentation / Conference Contribution
Farrenkopf, T., Guckert, M., Urquhart, N., & Wells, S. (2017, June). Information Diffusion in Multi-Agent Communities. Paper presented at 6th World Congress of the International Microsimulation Association, Moncalieri, Italy

Understanding the course of events when newly launched products penetrate a market, and how those products supersede existing dominant products, is crucial. Besides potential applications for business purposes the ability to simulate scenarios to mod... Read More about Information Diffusion in Multi-Agent Communities.

Monkeypuzzle: Towards Next Generation, Free & Open-Source, Argument Analysis Tools (2017)
Presentation / Conference Contribution
Douglas, J., & Wells, S. (2017, June). Monkeypuzzle: Towards Next Generation, Free & Open-Source, Argument Analysis Tools. Paper presented at The 17th International Workshop on Computation Models of Natural Argument (CMNA17)

We introduce a new, free, open-source, web-based argument analysis tool called Monkeypuzzle. This is designed to provide both a foundation for creating and visualising reproducible argument analyses as well as a flexible framework for investigating n... Read More about Monkeypuzzle: Towards Next Generation, Free & Open-Source, Argument Analysis Tools.

Automatically Detecting Fallacies in System Safety Arguments (2016)
Presentation / Conference Contribution
Yuan, T., Manandhar, S., Kelly, T., & Wells, S. (2015, October). Automatically Detecting Fallacies in System Safety Arguments. Presented at 15th International Workshop on Computational Models of Natural Argument (CMNA15), Bertinoro, Italy

Safety cases play a significant role in the development of safety-critical systems. The key components in a safety case are safety arguments, that are designated to demonstrate that the system is acceptably safe. Inappropriate reasoning with safety a... Read More about Automatically Detecting Fallacies in System Safety Arguments.

Ontology Based Business Simulations (2016)
Journal Article
Farrenkopf, T., Guckert, M., Urquhart, N., & Wells, S. (2016). Ontology Based Business Simulations. Journal of Artificial Societies and Social Simulation, 19(4), https://doi.org/10.18564/jasss.3266

Within business games there is a need to provide realistic feedback for decisions made, if such business games are to continue to remain relevant in increasingly complex business environments. We address this problem by using soware agents to simula... Read More about Ontology Based Business Simulations.

Combinatorial Dialogue Games in Strategic Argumentation (2016)
Book Chapter
Wells, S. (2016). Combinatorial Dialogue Games in Strategic Argumentation. In Argumentation and Reasoned Action Volume 2 (1045-1063). College Publications

We introduce combinatorial dialogue games, an approach to strategizing within argumentative dialogue games where the moves played are interpreted as moves within an edge addition and/or edge-removal combinatorial game. This enables an agent to reason... Read More about Combinatorial Dialogue Games in Strategic Argumentation.

Using argumentation within sustainable transport communication (2016)
Book Chapter
Wells, S., & Pangbourne, K. (2016). Using argumentation within sustainable transport communication. In Argumentation and Reasoned Action Volume 1 (781-801). College Publications

In this paper we present the preliminary results of a survey of persuasive communication within the sustainable transport domain. This survey is underpinned by a reconstruction of the arguments used, a scheme oriented analysis of the corpus of recon... Read More about Using argumentation within sustainable transport communication.

Large-scale Argument Visualization (LSAV) (2016)
Presentation / Conference Contribution
Khartabil, D., Wells, S., & Kennedy, J. (2016, June). Large-scale Argument Visualization (LSAV). Presented at 18th EG/VGTC Conference on Visualization

Arguments are structures of premises and conclusions that underpin rational reasoning processes. Within complex knowledge domains, especially if they are contentious, argument structures can become large and complex. Visualization tools have been dev... Read More about Large-scale Argument Visualization (LSAV).

Demo paper: AGADE - Scalability of ontology based agent simulations (2016)
Presentation / Conference Contribution
Farrenkopf, T., Guckert, M., Urquhart, N. B., & Wells, S. (2016, June). Demo paper: AGADE - Scalability of ontology based agent simulations. Presented at 14th International Conference on Practical Applications of Agents and Multi-Agent Systems, Sevilla, Spain

Simulations of real world scenarios often require considerably
large numbers of agents. With increasing level of detail and resolution
in the underlying models machine limitations both in the aspect of
memory and computing power are reached. Even... Read More about Demo paper: AGADE - Scalability of ontology based agent simulations.

Automatically Detecting Fallacies in System Safety Arguments (2015)
Presentation / Conference Contribution
Wells, S., Yuan, T., Manandhar, S., & Kelly, T. (2015, October). Automatically Detecting Fallacies in System Safety Arguments. Paper presented at 15th International Workshop on Computational Models of Natural Argument(CMNA15), Bertinoro, Italy

Safety cases play a significant role in the development of safety-critical systems. The key components in a safety case are safety arguments, that are designated to demonstrate that the system is acceptably safe. Inappropriate reasoning with safety a... Read More about Automatically Detecting Fallacies in System Safety Arguments.

Introducing ALIAS (2015)
Presentation / Conference Contribution
Wells, S., & LaGreca, R. (2015, October). Introducing ALIAS. Paper presented at 15th International Workshop on Computation Models of Natural Argument

ALIAS is a Python library for constructing, manipulating, storing, visualising, and converting argumentation structues. It is available with full source code under a copyleft license and aims to become a Swiss Army Knife for working with arguments in... Read More about Introducing ALIAS.

Using Argumentation Within Sustainable Transport Communication (2015)
Presentation / Conference Contribution
Wells, S., & Pangbourne, K. (2015, June). Using Argumentation Within Sustainable Transport Communication. Paper presented at 1st European Conference on Argumentation: Argumentation and Reasoned Action (ECA15)

See attached file.