12.4.3 RAG 파이프라인 - 리랭크 - RankZephyr Effective and Robust Zero-Shot Listwise Reranking is a Breeze! - GPT-4_이긴_70억_재순위_모델_랭크제퍼

12.4.3 RAG 파이프라인 - 리랭크 - RankVicuna Zero-Shot Listwise Document Reranking with Open-Source Large Language Models - GPT-4_성능_따라잡은_70억_오픈소스_랭크비쿠냐

12.4.3 RAG 파이프라인 - 리랭크 - Is ChatGPT Good at Search Investigating Large Language Models as Re-Ranking Agents - ChatGPT_검색_순위_능력을_흡수한_초소형_모델

12.4.3 RAG 파이프라인 - 리랭크 - Strategies for Effective and Efficient Text Ranking Using Large Language Models - 순위_매기기로_본_LLM의_치명적_약점

12.4.3 RAG 파이프라인 - 리랭크 - Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking - 문서_순위,_지시_튜닝은_오히려_독이_된다

12.4.3 RAG 파이프라인 - 리랭크 - ColBERT Efficient and Effective Passage Search via Contextualized Late Interaction over BERT - BERT보다_170배_빠른_검색_모델_ColBERT

12.4.2 RAG 파이프라인 - 검색 - A Multi-Task Embedder For Retrieval Augmented LLMs - 유사성_대신_유용성을_학습한_만능_검색기

12.4.2 RAG 파이프라인 - 검색 - Generative Retrieval with Few-shot Indexing - 훈련_필요_없는_퓨샷_생성형_검색

12.4.2 RAG 파이프라인 - 검색 - Transformer Memory as a Differentiable Search Index - 문서를_암기해_검색_인덱스가_된_구글_DSI

12.4.2 RAG 파이프라인 - 검색 - How Does Generative Retrieval Scale to Millions of Passages - 생성적_검색_성능은_모델이_클수록_떨어졌다