Confirmation Bias as a Cognitive Resource in LLM-Supported Deliberation

TL;DR

Problem: LLMs can induce conformity and reduce epistemic vigilance in group decision-making. Approach: a three-stage process leveraging confirmation bias with LLM-assisted articulation and simulated critique to scaffold productive disagreement while preserving epistemic ownership. Contributions: a practical framework for using LLMs as epistemic provocateurs in three preparatory stages and a theoretical synthesis with the Argumentative Theory of Reasoning. Significance: enables more robust group reasoning by balancing AI persuasion with human critical scrutiny, with potential to reduce groupthink and improve truth-seeking in collaborative settings.

Abstract

Large language models (LLMs) are increasingly used in group decision-making, but their influence risks fostering conformity and reducing epistemic vigilance. Drawing on the Argumentative Theory of Reasoning, we argue that confirmation bias, often seen as detrimental, can be harnessed as a resource when paired with critical evaluation. We propose a three-step process in which individuals first generate ideas independently, then use LLMs to refine and articulate them, and finally engage with LLMs as epistemic provocateurs to anticipate group critique. This framing positions LLMs as tools for scaffolding disagreement, helping individuals prepare for more productive group discussions.