Examination of whether LLMs can maintain consistency over extended multiple text generation for 10 medical personas. 5 novel plausibility metrics proposed, and an ontology of common LLM errors.
-
Updated
Jul 12, 2024 - Python
Examination of whether LLMs can maintain consistency over extended multiple text generation for 10 medical personas. 5 novel plausibility metrics proposed, and an ontology of common LLM errors.
Examples of using different retrievers in LangChain, including Wikipedia, Vector Store, MMR, MultiQuery, and Contextual Compression retrievers. Demonstrates how to fetch relevant context for semantic search, Q&A, summarization, and retrieval-augmented generation (RAG).
Structure‑aware RAG platform with semantic search and citations.
Development of a multilingual RAG architecture for financial advising using Maximal Marginal Relevance (MMR) and contextual compression to optimize token consumption and maximize source diversity.
A system based on the study by Aranzamendez, Bolito, and Rafe (2024) titled "An Enhancement of Content-based Filtering Applied in Movie Recommendation System."
Add a description, image, and links to the maximal-marginal-relevance topic page so that developers can more easily learn about it.
To associate your repository with the maximal-marginal-relevance topic, visit your repo's landing page and select "manage topics."