Similar Links:

• Precise Zero-Shot Dense Retrieval without Relevance Labels

• Text and Code Embeddings by Contrastive Pre-Training

• One Embedder, Any Task: Instruction-Finetuned Text Embeddings (INSTRUCTOR)

• Supporting document development with Concordia

• Design Of This Website

• Design Of This Website § Backlink

• Design Of This Website § Tags

• The complex dynamics of collaborative tagging

• Nenex: A Neural Personal Wiki Idea

• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

• RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

• A Neural Corpus Indexer for Document Retrieval

• Transformer Memory as a Differentiable Search Index

• Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?

• SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval

• Rethinking Search: Making Domain Experts out of Dilettantes

• Contextual Document Embeddings

• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching

• The Case for Learned Index Structures

• Search: GS; Google; site