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

arXiv: https://arxiv.org/abs/2505.05298 · HTML: https://mlsanity.com/paper/2505.05298/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 7 of 7)

- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Argumentative Large Language Models for Explainable and Contestable Claim Verification](https://mlsanity.com/paper/2405.02079/) (2024)
- [Evaluating the Robustness of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2411.14215/) (2024)
- [Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments](https://mlsanity.com/paper/2404.09329/) (2024)
- [Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions](https://mlsanity.com/paper/2502.12616/) (2025)
- [Implicit Bias in LLMs: A Survey](https://mlsanity.com/paper/2503.02776/) (2025)

## Built on by (most cited first, 3 of 3)

- [The Thin Line Between Comprehension and Persuasion in LLMs](https://mlsanity.com/paper/2507.01936/) (2025)
- [Investigating Multi-Agent Deliberation in Law](https://mlsanity.com/paper/2606.30906/) (2026)
- [Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks](https://mlsanity.com/paper/2609.28673/) (2026)

## Abstract (arXiv)

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 skills rather than replacing them. We introduce the concept of textitreasonable 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.