Zzong's Notes

Home

❯

Retrieval

❯

rag

❯

Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation

Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation

2026년 8월 29일1 min read

[2504.05731] Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation


함께 보면 좋은 글

Retrieval-Augmented Generation

RAG is a method that retrieves relevant information from a knowledge base and appends it to the user’s prompt, significantly enhancing the model’s response.

xRAG

Retrieval-Augmented Generation (RAG) 시스템의 효율성을 극대화하기 위한 새로운 문맥 압축 방법론인 xRAG를 제안합니다.

CalibRAG

한줄 요약 RAG에서 검색된 문서로 사용자가 올바른 의사결정을 내릴 확률을 예측하는 forecasting function f(t,q,d)를 학습하여, 문서 reranking과 confidence calibration을 동시에 달성하는 프레임워크.

SimpleX - A Simple and Strong Baseline for Collaborative Filtering

Introduction learning process of collaborative filtering 는 크게 3 개의 요소로 나뉘어진다: 1) interaction encoder, 2)loss functions, 3)negative sampling 적은 negative sampling 과 BPR loss 로...

Context Precision

Context Precision은 RAGAS에서 retriever가 가져온 context 중 실제 답변에 도움이 되는 context가 상위 rank에 잘 배치되어 있는지를 보는 지표다.

Collaborative Topic Modeling for Recommending GitHub Repositories

References paper link: www.cs.cmu.edu/afs/cs.cmu.edu/Web/People/norii/pub/github-ctr.pdf .

A Survey on Reinforcement Learning for Recommender Systems

References paper link: arxiv.org/pdf/2109.10665.pdf Reinforcement Learning based Recommender Systems: A Survey .

Collaborative Filtering for Implicit Feedback Datasets

Alternating Least Squares Vs.

Matrix Factorization for Collaborative Filtering Is Just Solving an Adjoint Latent Dirichlet Allocation Model After All

Conclusion LDA4Rec model, which extends the traditional LDA by incorporating parameters for the popularity of items and conformity of users.

A New HOPE, Domain-agnostic Automatic Evaluation of Text Chunking

A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking.