BartAmin / Fine-tuned-RAGView on GitHub
I developed a fine-tuned retrieval head for RAG that learns to more reliably retrieve relevant passages by transforming the query embeddings before retrieval. It is trained on synthetically generated question-chunk pairs from the corpus, and benchmarked against standard top-K cosine similarity on the isaacus/legal-rag-bench legal corpus.
17May 21, 2026Updated last month

Alternatives and similar repositories for Fine-tuned-RAG

Users that are interested in Fine-tuned-RAG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?