向着具有人类情景记忆的大型语言模型发展。

IF 17.2 1区 心理学 Q1 BEHAVIORAL SCIENCES
Cody V Dong, Qihong Lu, Kenneth A Norman, Sebastian Michelmann
{"title":"向着具有人类情景记忆的大型语言模型发展。","authors":"Cody V Dong, Qihong Lu, Kenneth A Norman, Sebastian Michelmann","doi":"10.1016/j.tics.2025.06.016","DOIUrl":null,"url":null,"abstract":"<p><p>Cognitive neuroscience research has made tremendous progress over the past decade in addressing how episodic memory (EM; memory for unique past experiences) supports our ability to understand real-world events. Despite this progress, we still lack a computational modeling framework that is able to generate precise predictions regarding how EM will be used when processing high-dimensional naturalistic stimuli. Recent work in machine learning that augments large language models (LLMs) with external memory could potentially accomplish this, but current popular approaches are misaligned with human memory in various ways. This review surveys these differences, suggests criteria for benchmark tasks to promote alignment with human EM, and ends with potential methods to evaluate predictions from memory-augmented models using neuroimaging techniques.</p>","PeriodicalId":49417,"journal":{"name":"Trends in Cognitive Sciences","volume":" ","pages":""},"PeriodicalIF":17.2000,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Towards large language models with human-like episodic memory.\",\"authors\":\"Cody V Dong, Qihong Lu, Kenneth A Norman, Sebastian Michelmann\",\"doi\":\"10.1016/j.tics.2025.06.016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Cognitive neuroscience research has made tremendous progress over the past decade in addressing how episodic memory (EM; memory for unique past experiences) supports our ability to understand real-world events. Despite this progress, we still lack a computational modeling framework that is able to generate precise predictions regarding how EM will be used when processing high-dimensional naturalistic stimuli. Recent work in machine learning that augments large language models (LLMs) with external memory could potentially accomplish this, but current popular approaches are misaligned with human memory in various ways. This review surveys these differences, suggests criteria for benchmark tasks to promote alignment with human EM, and ends with potential methods to evaluate predictions from memory-augmented models using neuroimaging techniques.</p>\",\"PeriodicalId\":49417,\"journal\":{\"name\":\"Trends in Cognitive Sciences\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":17.2000,\"publicationDate\":\"2025-07-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Trends in Cognitive Sciences\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1016/j.tics.2025.06.016\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BEHAVIORAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Trends in Cognitive Sciences","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1016/j.tics.2025.06.016","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BEHAVIORAL SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

在过去的十年里,认知神经科学研究在解决情景记忆(EM;记忆(独特的过去经历)支持我们理解现实世界事件的能力。尽管取得了这一进展,但我们仍然缺乏一个计算建模框架,能够准确预测EM在处理高维自然刺激时将如何使用。最近在机器学习领域的工作是用外部记忆增强大型语言模型(llm),这可能会实现这一目标,但目前流行的方法在很多方面都与人类记忆不一致。这篇综述调查了这些差异,提出了基准任务的标准,以促进与人类EM的一致性,并以使用神经成像技术评估记忆增强模型预测的潜在方法作为结束。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Towards large language models with human-like episodic memory.

Cognitive neuroscience research has made tremendous progress over the past decade in addressing how episodic memory (EM; memory for unique past experiences) supports our ability to understand real-world events. Despite this progress, we still lack a computational modeling framework that is able to generate precise predictions regarding how EM will be used when processing high-dimensional naturalistic stimuli. Recent work in machine learning that augments large language models (LLMs) with external memory could potentially accomplish this, but current popular approaches are misaligned with human memory in various ways. This review surveys these differences, suggests criteria for benchmark tasks to promote alignment with human EM, and ends with potential methods to evaluate predictions from memory-augmented models using neuroimaging techniques.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Trends in Cognitive Sciences
Trends in Cognitive Sciences 医学-行为科学
CiteScore
27.90
自引率
1.50%
发文量
156
审稿时长
6-12 weeks
期刊介绍: Essential reading for those working directly in the cognitive sciences or in related specialist areas, Trends in Cognitive Sciences provides an instant overview of current thinking for scientists, students and teachers who want to keep up with the latest developments in the cognitive sciences. The journal brings together research in psychology, artificial intelligence, linguistics, philosophy, computer science and neuroscience. Trends in Cognitive Sciences provides a platform for the interaction of these disciplines and the evolution of cognitive science as an independent field of study.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信