Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions

📅 2024-06-16
📈 Citations: 2
Influential: 0
📄 PDF

career value

147K/year
🤖 AI Summary
This work challenges the conventional paradigm of eliminating all cognitive biases, instead investigating how large language models (LLMs) can *consciously leverage* cognitive biases to improve multiple-choice decision-making. Method: We propose the “bias-as-resource” perspective, designing a heuristic modulation strategy and a confidence-driven abstention mechanism; we further introduce BRU—the first bias-aware multiple-choice framework—and a balanced, expert-annotated evaluation dataset for bias analysis. Contribution/Results: Our approach achieves human–model reasoning alignment and bias-directed calibration, significantly improving accuracy, reducing error rates, and enhancing response efficiency—while preserving logical rigor. Crucially, this is the first work to formalize human cognitive biases as *controllable variables* rather than noise, establishing a novel LLM decision-optimization paradigm that jointly ensures practical utility and reliability.

Technology Category

Application Category

📝 Abstract
This paper examines the role of cognitive biases in the decision-making processes of large language models (LLMs), challenging the conventional goal of eliminating all biases. When properly balanced, we show that certain cognitive biases can enhance decision-making efficiency through rational deviations and heuristic shortcuts. By introducing heuristic moderation and an abstention option, which allows LLMs to withhold responses when uncertain, we reduce error rates, improve decision accuracy, and optimize decision rates. Using the Balance Rigor and Utility (BRU) dataset, developed through expert collaboration, our findings demonstrate that targeted inspection of cognitive biases aligns LLM decisions more closely with human reasoning, enhancing reliability and suggesting strategies for future improvements. This approach offers a novel way to leverage cognitive biases to improve the practical utility of LLMs across various applications.
Problem

Research questions and friction points this paper is trying to address.

Examines cognitive biases in LLM decision-making for MCQs
Proposes heuristic moderation to reduce errors and improve accuracy
Aligns LLM decisions with human reasoning using BRU dataset
Innovation

Methods, ideas, or system contributions that make the work stand out.

Leveraging cognitive biases for efficiency
Introducing heuristic moderation techniques
Using abstention to reduce error rates
🔎 Similar Papers
No similar papers found.