Confirmation Bias as a Cognitive Resource in LLM-Supported Deliberation

2025-09-18

AI Summary

Large language models (LLMs) often exacerbate confirmation bias and erode cognitive vigilance in group decision-making. Method: This paper proposes a “bias transformation” framework: individuals first generate ideas independently, then leverage LLMs to refine expression, and finally employ LLMs to simulate adversarial critique—thereby pre-enacting group deliberation. Grounded in argumentation theory, the framework implements an LLM-driven, three-stage interactive process—claim distillation, adversarial simulation, and rebuttal preparation—reconfiguring LLMs from bias amplifiers into cognitive scaffolds. Contribution/Results: Empirical evaluation demonstrates significant improvements in individual argument quality, sensitivity to dissenting views, and readiness for counterargumentation. The framework enhances collective decision-making along three critical dimensions: depth, diversity, and inclusivity—transforming confirmation bias from a cognitive flaw to a catalyst for constructive epistemic divergence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Argumentation
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Harnessing confirmation bias as cognitive resource
• Reducing conformity in LLM-supported group decision-making
• Using LLMs as epistemic provocateurs for deliberation

Innovation

• Harnessing confirmation bias as cognitive resource
• Three-step process with independent idea generation
• LLMs as epistemic provocateurs scaffolding disagreement