Large language models (LLMs) match and sometimes exceed human performance in many domains. This study explores the potential of LLMs to augment human judgment in a forecasting task. We evaluate the effect on human forecasters of two LLM assistants: one designed to provide high-quality (‘superforecasting’) advice, and the other designed to be overconfident and base-rate neglecting, thus providing noisy forecasting advice. We compare participants using these assistants to a control group that received a less advanced model that did not provide numerical predictions or engage in explicit discussion of predictions. Participants (N = 991) answered a set of six forecasting questions and had the option to consult their assigned LLM assistant throughout. Our preregistered analyses show that interacting with each of our frontier LLM assistants significantly enhances prediction accuracy by between 24% and 28% compared to the control group. Exploratory analyses showed a pronounced outlier effect in one forecasting item, without which we find that the superforecasting assistant increased accuracy by 41%, compared with 29% for the noisy assistant. We further examine whether LLM forecasting augmentation disproportionately benefits less skilled forecasters, degrades the wisdom-of-the-crowd by reducing prediction diversity, or varies in effectiveness with question difficulty. Our data do not consistently support these hypotheses. Our results suggest that access to a frontier LLM assistant, even a noisy one, can be a helpful decision aid in cognitively demanding tasks compared to a less powerful model that does not provide specific forecasting advice. However, the effects of outliers suggest that further research into the robustness of this pattern is needed.

Philipp Schoenegger

Peter S. Park

Ezra Karger

Sean Trott

Philip E. Tetlock

ACM Transactions on Interactive Intelligent Systems

ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS (TIIS) 发表有关包含某种形式的机器智能的交互式系统的设计、实现或评估的研究论文。 TIIS 文章来自广泛的研究领域和社区。一篇文章可以采用交互式智能系统的几种互补观点中的任何一种，重点关注：智能技术、用户与系统的交互，或同时关注这两个方面。

ACM Transactions on Interactive Intelligent Systems (TIIS) publishes research papers on the design, implementation, or evaluation of interactive intelligent systems that incorporate some form of machine intelligence. Articles in TIIS come from a wide range of research fields and communities. Each paper may adopt any of several complementary perspectives on interactive intelligent systems, focusing on intelligent technologies, user-system interaction, or both aspects simultaneously.

《ACM Transactions on Interactive Intelligent Systems》 (TIIS) 发表关于交互式智能系统的设计、实现或评估的研究论文，这些系统包含某种形式的机器智能。TIIS 的文章涵盖广泛的研究领域和社区。每篇文章可以从多个互补的视角探讨交互式智能系统，重点关注智能技术、用户与系统的交互，或同时关注这两个方面。

Category	Quartile
计算机科学	4
计算机科学, 计算机人工智能	4

AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE	2