Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 16 Jun 2024.
Builds on
26 of 42 references.
References · 26
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023GPT-4 Technical Reportcited by 18,396
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
- 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
- 2023Bias and Fairness in Large Language Models: A Surveycited by 639
- 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 565
- 2024Large Language Models: A Surveycited by 525
14 more
- 2022Using cognitive psychology to understand GPT-3cited by 398
- 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
- 2024Cognitive Bias in Decision-Making with LLMscited by 106
- 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
- 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
- 2021Multi-Modal Answer Validation for Knowledge-Based VQAcited by 79
- 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluationcited by 75
- 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)cited by 58
- 2024Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinationscited by 54
- 2023Adaptation with Self-Evaluation to Improve Selective Prediction in LLMscited by 50
- 2023Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5cited by 42
- 2024Uncertainty quantification in fine-tuned LLMs using LoRA ensemblescited by 37
- 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 16
- 2024Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMscited by 13
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.