Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

arxiv-2024-A Survey on Large Language Models for Recommendation #372

Open
BrambleXu opened this issue Aug 5, 2024 · 0 comments
Open

arxiv-2024-A Survey on Large Language Models for Recommendation #372

BrambleXu opened this issue Aug 5, 2024 · 0 comments
Assignees
Labels
LLM(M) Large language models Recommendation(T) Recommendation Task Survey Survey/Review

Comments

@BrambleXu
Copy link
Owner

Summary:

为了全面了解现有基于LLM的推荐系统,本调查提出了一种分类法,将这些模型分为两大范式,分别是用于推荐的判别式LLM(DLLM4Rec)和用于推荐的生成式LLM(GLLM4Rec)

Resource:

  • pdf
  • [code](
  • [paper-with-code](

Paper information:

  • Author:
  • Dataset:
  • keywords:

Notes:
image

image

将item和user信息结合到一起,然后输入到RS里

image
  1. LLM 嵌入 + RS。这种建模范式将语言模型视为特征提取器,将物品和用户的特征输入LLMs并输出相应的嵌入。传统的 RS 模型可以利用知识感知嵌入来完成各种推荐任务。
  2. LLM 令牌 + RS。与前一种方法类似,这种方法根据输入的项目和用户特征生成令牌。生成的令牌通过语义挖掘捕捉潜在的偏好,可以集成到推荐系统的决策过程中。
  3. LLM 作为 RS。不同于(1)和(2),这种范式旨在将预训练的 LLM 直接转化为强大的推荐系统。输入序列通常包括个人资料描述、行为提示和任务指令。
image image image image

Model Graph:

Result:

Thoughts:

user-item是典型的RS问题,但是对于特殊的场景,没有history。数据形式不一样,sub领域只有匹配,看起来更像是检索,而不是推荐系统的领域。

Next Reading:

@BrambleXu BrambleXu added Survey Survey/Review Recommendation(T) Recommendation Task LLM(M) Large language models labels Aug 5, 2024
@BrambleXu BrambleXu self-assigned this Aug 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
LLM(M) Large language models Recommendation(T) Recommendation Task Survey Survey/Review
Projects
None yet
Development

No branches or pull requests

1 participant