Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design

In this position paper, we advocate for the development of conversational technology that is inherently designed to support and facilitate argumentative processes. We argue that, at present, large language models (LLMs) are inadequate for this purpose, and we propose an ideal technology design aimed at enhancing argumentative skills. This involves re-framing LLMs as tools to exercise our critical thinking rather than replacing them. We introduce the concept of 'reasonable parrots' that embody the fundamental principles of relevance, responsibility, and freedom, and that interact through argumentative dialogical moves. These principles and moves arise out of millennia of work in argumentation theory and should serve as the starting point for LLM-based technology that incorporates basic principles of argumentation.

A Logic Programming Approach to Global Logistics in a Co-Design Environment

In a co-design environment changes need to be integrated quickly and in an automated manner. This paper considers the challenge of creating and optimizing a global logistics system for the construction of a passenger aircraft within a co-design approach with respect to key performance indicators (like cost, time or resilience). The product in question is an aircraft, comprised of multiple components, manufactured at multiple sites worldwide. The goal is to find an optimal way to build the aircraft taking into consideration the requirements for its industrial system. The main motivation for approaching this challenge is to develop the industrial system in tandem with the product and making it more resilient against unforeseen events, reducing the risks of bottlenecks in the supply chain. This risk reduction ensures continued efficiency and operational success. To address this challenging and complex task we have chosen Answer Set Programming (ASP) as the modeling language, formalizing the relevant requirements of the investigated industrial system. The approach presented in this paper covers three main aspects: the extraction of the relevant information from a knowledge graph, the translation into logic programs and the computation of existing configurations guided by optimization criteria. Finally we visualize the results for an effortless evaluation of these models. Internal results seem promising and yielded several new research questions for future improvements of the discussed use case.

A Quantitative Symbolic Approach to Individual Human Reasoning

Cognitive theories for reasoning are about understanding how humans come to conclusions from a set of premises. Starting from hypothetical thoughts, we are interested which are the implications behind basic everyday language and how do we reason with them. A widely studied topic is whether cognitive theories can account for typical reasoning tasks and be confirmed by own empirical experiments. This paper takes a different view and we do not propose a theory, but instead take findings from the literature and show how these, formalized as cognitive principles within a logical framework, can establish a quantitative notion of reasoning, which we call plausibility. For this purpose, we employ techniques from non-monotonic reasoning and computer science, namely, a solving paradigm called answer set programming (ASP). Finally, we can fruitfully use plausibility reasoning in ASP to test the effects of an existing experiment and explain different majority responses.

Computational Argumentation and Cognition

This paper examines the interdisciplinary research question of how to integrate Computational Argumentation, as studied in AI, with Cognition, as can be found in Cognitive Science, Linguistics, and Philosophy. It stems from the work of the 1st Workshop on Computational Argumentation and Cognition (COGNITAR), which was organized as part of the 24th European Conference on Artificial Intelligence (ECAI), and took place virtually on September 8th, 2020. The paper begins with a brief presentation of the scientific motivation for the integration of Computational Argumentation and Cognition, arguing that within the context of Human-Centric AI the use of theory and methods from Computational Argumentation for the study of Cognition can be a promising avenue to pursue. A short summary of each of the workshop presentations is given showing the wide spectrum of problems where the synthesis of the theory and methods of Computational Argumentation with other approaches that study Cognition can be applied. The paper presents the main problems and challenges in the area that would need to be addressed, both at the scientific level but also at the epistemological level, particularly in relation to the synthesis of ideas and approaches from the various disciplines involved.