RAG
562 papers with code • 0 benchmarks • 4 datasets
Retrieval-Augmented Generation (RAG) is a task that combines the strengths of both retrieval-based models and generation-based models. In this approach, a retrieval system selects relevant documents or passages from a large corpus, and a generation model, typically a neural language model, uses the retrieved information to generate a response. This method enhances the accuracy and coherence of generated text, especially in tasks requiring detailed knowledge or long context handling.
RAG is particularly useful in open-domain question answering, knowledge-grounded dialogue, and summarization tasks. The retrieval step helps the model to access and incorporate external information, making it less reliant on memorized knowledge and better suited for generating responses based on the latest or domain-specific information.
The performance of RAG systems is usually measured using metrics such as precision, recall, F1 score, BLEU score, and exact match. Some popular datasets for evaluating RAG models include Natural Questions, MS MARCO, TriviaQA, and SQuAD.
Benchmarks
These leaderboards are used to track progress in RAG
Libraries
Use these libraries to find RAG models and implementations
PeerQA
CRSB
Most implemented papers
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
huggingface/transformers
•
•
NeurIPS 2020
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens.
Retrieval-Augmented Generation for Large Language Models: A Survey
Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes.
Robust affine point matching via quadratic assignment on Grassmannians
Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds.
RAGAS: Automated Evaluation of Retrieval Augmented Generation
We introduce RAGAs (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines.
RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
Retrieval-augmented generation (RAG) has become a main technique for alleviating hallucinations in large language models (LLMs).
The Power of Noise: Redefining Retrieval for RAG Systems
florin-git/The-Power-of-Noise
•
•
Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system.
Retrieval-Augmented Generation for AI-Generated Content: A Survey
We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators.
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
To combine the strengths of these contrasting methods, we propose a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed.
LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation
Specifically, we first utilize LRP to compute the relevance between the input and output of the RAG generator.
