Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Inductive Reasoning00:59

Inductive Reasoning

64.7K
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...
64.7K
Probability Laws01:49

Probability Laws

43.9K
Overview
43.9K
Language and Cognition01:27

Language and Cognition

704
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
704
Deductive Reasoning01:16

Deductive Reasoning

63.9K
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...
63.9K
Probability in Statistics01:14

Probability in Statistics

22.1K
Probability is the likelihood of an event occurring. The term event is defined as a collection of results of a procedure. An event is a simple event when an outcome cannot be divided into simpler parts.
An example of a simple event is a coin toss. The result of a coin toss is either a head or a tail. Here, head and tail are two simple events. These two simple events make up the sample space. Further, the probability of an event occurring falls within the range of 0 to 1. The probability of an...
22.1K
Language Development01:22

Language Development

831
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
831

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Evaluation of the association between MREPT-derived conductivity and IVIM-derived ISF-related metrics in the brains of patients with cognitive impairments.

Frontiers in aging neuroscience·2026
Same author

Development of an Artificial Intelligence Model to Predict Endotracheal Intubation in Critically Ill Patients in Real Time.

Journal of clinical medicine·2026
Same author

Empowerment gain and causal model construction: children and adults are sensitive to controllability and variability in their causal interventions.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same author

Evaluation of conductivity tensor image along the perivascular space in the brains of patients with cognitive impairments.

Frontiers in aging neuroscience·2026
Same author

Relationships between heart rate-based training load and running metrics in field hockey players.

The Journal of sports medicine and physical fitness·2026
Same author

AI-Driven Predictions of Readmission and Mortality for Improved Discharge Decisions in Critical Care: A Retrospective Study.

Diagnostics (Basel, Switzerland)·2026
Same journal

Interplay between oxygen redox and interfacial stability of Li-rich positive electrodes in sulfide-based all-solid-state batteries.

Nature communications·2026
Same journal

Breaking dependence on melanisation imparts diversity to a dogmatic invasion strategy of phytopathogenic fungi.

Nature communications·2026
Same journal

Hydroxyl-rich nanocavities on perovskite enable nearly barrierless intramolecular hydrogen transfer for nitrate electroreduction to ammonia.

Nature communications·2026
Same journal

Household mobility responses to weather extremes in Kyrgyzstan.

Nature communications·2026
Same journal

Autonomous Motion Vision with Tri-bulk-heterojunctioned Organic Adaptation Transistor.

Nature communications·2026
Same journal

Tissue-adhesive hydrogel optical fiber for peripheral optogenetic neuromodulation.

Nature communications·2026
查看所有相关文章

相关实验视频

Updated: Jan 13, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

贝叶斯教学使大语言模型中的概率推理成为可能.

Linlu Qiu1, Fei Sha2, Kelsey Allen3,4,5

  • 1Massachusetts Institute of Technology, Cambridge, MA, USA. linluqiu@mit.edu.

Nature communications
|January 7, 2026
PubMed
概括
此摘要是机器生成的。

大型语言模型 (LLM) 可以学习贝叶斯推理技能. 教导LLM模仿贝叶斯预测显著提高了他们的信念更新和对新任务的概括能力.

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

相关实验视频

Last Updated: Jan 13, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

科学领域:

  • 人工智能的人工智能
  • 认知科学 认知科学
  • 机器学习 机器学习

背景情况:

  • 大型语言模型 (LLM) 越来越多地被部署为与用户和环境交互的代理.
  • 有效的代理行为需要构建世界表征和概率学信仰.
  • 个性化推需要LLM从交互历史中推断用户偏好.

研究的目的:

  • 评估LLMs的信念更新能力与规范贝叶斯推理框架相比.
  • 调查教学LLM模仿贝叶斯模型是否提高他们的推理和概括能力.

主要方法:

  • 根据贝叶斯标准评估了LLM的信念更新性能.
  • 经过训练,LLM可以模拟规范贝叶斯模型的预测.
  • 评估了学习的信念更新技能对新任务的概括性.

主要成果:

  • 在遵守贝叶斯的信念更新框架方面,LLM表现出显著的缺陷.
  • 训练LLM模仿贝叶斯预测导致了对信念更新的大幅度改进.
  • 增强的信念更新能力有效地对未见的任务进行了概括.

结论:

  • 与贝叶斯代理相比,LLM在最佳信念更新方面表现出局限性.
  • 通过模仿贝叶斯模型的学习,LLM可以获得和概括推理技能,特别是信念更新.
  • 这项研究强调了LLM从数据中学习复杂推理能力的潜力.