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

2025-05-08

AI Summary

Current large language models (LLMs) inadequately support argumentative reasoning, often substituting for—rather than cultivating—human critical thinking. Method: This paper proposes the “Reasonable Parrot” paradigm, reframing LLMs as dialectical dialogue collaborators. It systematically incorporates the triad of classical argumentation principles—relevance, accountability, and freedom—grounded in millennia of argumentation theory, and designs a dialogical turn-taking architecture integrating dialogical logic and human-AI collaboration. Methodologically, it unifies argumentation theory, dialogical logic, and explainable AI (XAI) to formally specify normative conversational behavior boundaries for LLMs. Contribution: The work establishes a novel technical evaluation standard centered on augmenting human argumentative competence. It provides a foundational design framework for explainable, negotiable, and responsible AI systems, advancing principled human-AI co-reasoning beyond mere response generation.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• LLMs lack inherent design for argumentative processes
• Proposing ideal technology to enhance argumentative skills
• Introducing 'reasonable parrots' with argumentation theory principles

Innovation

• Design LLMs to support argumentative processes
• Reframe LLMs as critical thinking tools
• Incorporate argumentation theory principles