RepositoryHuskyInSalt/CRAGResearch
Standard RAG setups fail when retrieval returns incorrect or noisy contexts, leading to hallucinations. CRAG introduces an active validation and fallback step, significantly improving generation robustness in knowledge-driven AI workflows.
CRAG addresses a primary bottleneck in current RAG systems: blind trust in retrieval output. By introducing confidence grading, secondary search fallbacks, and fine-grained passage rewriting, it reduces hallucinations. The codebase runs on Python 3.11 with fine-tuned LLaMA-2 checkpoints. However, as an academic repository lacking an explicit open-source licence, it functions primarily as an experimental reference implementation rather than an out-of-the-box production library.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Repository:AkariAsai/self-rag
SELF-RAG is an open-source framework designed to train language models to adaptively retrieve external passages, generate responses, and critique their own outputs using fine-grained reflection tokens.
2.4kstarsPython
Repository:OpenSPG/KAG
KAG (Knowledge Augmented Generation) is an open-source framework combining LLMs with the OpenSPG engine. It aims to address the limitations of vector similarity in standard RAG and noise in OpenIE-based GraphRAG for domain-specific applications.
9kstarsPython
Repository:OSU-NLP-Group/HippoRAG
HippoRAG (now in version 2) is an open-source memory framework for LLMs developed by the OSU NLP Group, combining knowledge graphs and Personalized PageRank to mimic human long-term memory across external documents.
4kstarsPython
Repository:hhhuang/CAG
The CAG open-source repository introduces Cache-Augmented Generation as an alternative to Retrieval-Augmented Generation (RAG). By preloading the entire knowledge base into the context window and reusing the precomputed KV cache, it bypasses real-time document retrieval entirely.
1.5kstarsPython
Repository:parthsarthi03/raptor
RAPTOR provides the official Python implementation of a tree-based RAG framework that recursively clusters and summarises documents, improving retrieval quality across large texts.
1.8kstarsPython
Article:Lei Liang et al.
A research team led by Lei Liang introduces Knowledge Augmented Generation (KAG), a framework extending conventional RAG with knowledge graphs to address logic, temporal, and numerical reasoning deficits in specialised domains.
Parts of this content were created with the assistance of AI.
