启发式
计算机科学
概括性
集合(抽象数据类型)
可扩展性
秩(图论)
空格(标点符号)
功能(生物学)
人工智能
数据科学
理论计算机科学
机器学习
程序设计语言
数学
组合数学
心理治疗师
操作系统
生物
进化生物学
数据库
心理学
作者
Bernardino Romera‐Paredes,Mohammadamin Barekatain,Alexander Novikov,Matej Balog,Manish Kumar,Emilien Dupont,Francisco J. R. Ruiz,Jordan S. Ellenberg,Pengming Wang,Omar Fawzi,Pushmeet Kohli,Alhussein Fawzi
出处
期刊:Nature
[Springer Nature]
日期:2023-12-14
卷期号:625 (7995): 468-475
被引量:48
标识
DOI:10.1038/s41586-023-06924-6
摘要
Abstract Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements 1,2 . This hinders the use of current large models in scientific discovery. Here we introduce FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator. We demonstrate the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches 3 . Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we discover new constructions of large cap sets going beyond the best-known ones, both in finite dimensional and asymptotic cases. This shows that it is possible to make discoveries for established open problems using LLMs. We showcase the generality of FunSearch by applying it to an algorithmic problem, online bin packing, finding new heuristics that improve on widely used baselines. In contrast to most computer search approaches, FunSearch searches for programs that describe how to solve a problem, rather than what the solution is. Beyond being an effective and scalable strategy, discovered programs tend to be more interpretable than raw solutions, enabling feedback loops between domain experts and FunSearch, and the deployment of such programs in real-world applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI