相关实验视频

Updated: Mar 2, 2026

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

推论计算缩放的理论:通过指导随机技能搜索进行推理

Austin R Ellis-Mohr¹, Anuj K Nayak¹, Lav R Varshney^1,2

¹Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences

|February 28, 2026

概括

大型语言模型 (LLM) 的推断是昂贵的. 定向随机技能搜索 (DS3) 通过将其建模为技能图表穿越来优化LLM推理,提高效率和资源配置.

科学领域:

人工智能的人工智能
机器学习机器学习
计算语言学计算语言学

背景情况:

大型语言模型 (LLM) 需要大量的计算和能源来培训和部署.
推断成本越来越令人担忧,特别是在复杂的推理任务中,目前的计算优化模型可能会忽略它.
现有的框架经常单独分析模型大小,数据集大小,并推断令牌,缺少高效的操作点.

研究的目的:

引入指向随机技能搜索 (DS3),这是一个优化LLM推理的新框架.
为LLM培训和推断相互依赖提供统一的理论理解.
实现基于原则的算法设计和资源分配,以实现可持续的AI.

主要方法:

将LLM推理表示为在学习技能图表上的随机穿越.
为各种推理策略,如思维链 (CoT) 和思维树 (ToT) 来导出任务成功和计算成本的闭式表达式.
扩展以前的图表框架,包括LLM培训和推理,将DS3与实证缩放规律相结合.

主要成果:

在理论上,DS3框架可以恢复观察到的模式,包括用日志计算进行线性精度缩放.
基于任务难度和模型能力的最佳推理策略的证明变化.
在一个单一的框架内统一的最佳和多数投票 (MV) 推断策略.

结论:

DS3提供了对LLM推断效率的更深入的理论理解.
该框架支持基于原则的算法设计选择和人工智能资源分配.
强调考虑培训-推理相互依赖性对于可持续的AI发展的重要性.

关键词:

推断缩放的推论缩放.推断时间计算推断时间计算大型语言模型.推理推理推理缩放规则的法律,缩放规则的法律.测试时间计算列车时间计算

更多相关视频

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task

Published on: July 22, 2025

相关概念视频

Inductive Reasoning

Inductive Reasoning

Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...

Reasoning

Reasoning

Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...

Deductive Reasoning

Deductive Reasoning

Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...

Statically Indeterminate Problem Solving

Statically Indeterminate Problem Solving

Statically indeterminate problems are those where statics alone can not determine the internal forces or reactions. Consider a structure comprising two cylindrical rods made of steel and brass. These rods are joined at point B and restrained by rigid supports at points A and C. Now, the reactions at points A and C and the deflection at point B are to be determined. This rod structure is classified as statically indeterminate as the structure has more supports than are necessary for maintaining...

Theory of Attribution I: Correspondent Inference Theory

Theory of Attribution I: Correspondent Inference Theory

Correspondent inference theory, proposed by Jones and Davis in 1965, seeks to explain how individuals infer stable personality traits from observed behaviors. It suggests that people attribute actions to underlying dispositions rather than external circumstances, particularly when the behavior appears intentional and socially significant.Voluntary Behavior and Dispositional AttributionAccording to this theory, individuals are more likely to attribute behavior to personal traits when it appears...

Reason and Intuition

Reason and Intuition

The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...