SemanticScuttle - klotz.me

klotz: rag* + text*

Bookmarks on this page are managed by an admin user.

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

1. Combining the Best of Both Worlds: Retrieval-Augmented Generation for Knowledge-Intensive Natural Language Processing

   This article discusses Retrieval-Augmented Generation (RAG) models, a new approach that addresses the limitations of traditional models in knowledge-intensive Natural Language Processing (NLP) tasks. RAG models combine parametric memory from pre-trained seq2seq models with non-parametric memory from a dense vector index of Wikipedia, enabling dynamic knowledge access and integration.

   2024-05-28 Tags: retrieval-augmented generation, nlp, llm, parametric memory by klotz
2. Overcoming the Limits of RAG with ColBERT

   ColBERT is a new way of scoring passage relevance using a BERT language model that substantially solves the problems with dense passage retrieval.

   2024-03-12 Tags: llm, rag, embedding, bert, colbert, cosine distance, concept expansion by klotz
3. Multi-Vector Retriever for RAG on tables, text, and images

   2023-10-22 Tags: llm, rag, langchain, multi-modal, text, column, image by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0