Bounded Minds, Generative Machines: Envisioning Conversational AI that Works with Human Heuristics and Reduces Bias Risk
Jiqun Liu
TL;DR
The paper addresses how conversational AI can coexist with human heuristics rather than fight them, arguing that bounded rationality shapes user reasoning in dynamic, multi-turn interactions. It outlines a research pathway focusing on detecting cognitive vulnerability, supporting judgment under uncertainty, and evaluating decision quality and cognitive robustness beyond factual accuracy, while integrating governance considerations. Key mechanisms include signals such as viewpoint diversity and calibration failures, lightweight interventions like baseline surfacing and uncertainty ranges, and retrieval-augmented generation to provide diverse, grounded perspectives. The work highlights practical safeguards and governance processes, including audit trails and model cards, to reduce bias risk and cognitive manipulation, offering a strategic roadmap for responsible, cognitively aware AI design and evaluation.
Abstract
Conversational AI is rapidly becoming a primary interface for information seeking and decision making, yet most systems still assume idealized users. In practice, human reasoning is bounded by limited attention, uneven knowledge, and reliance on heuristics that are adaptive but bias-prone. This article outlines a research pathway grounded in bounded rationality, and argues that conversational AI should be designed to work with human heuristics rather than against them. It identifies key directions for detecting cognitive vulnerability, supporting judgment under uncertainty, and evaluating conversational systems beyond factual accuracy, toward decision quality and cognitive robustness.