HSLiu-Initial/CtrlA
This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.
This project helps large language models (LLMs) generate more accurate and honest answers by dynamically adjusting how they use their built-in knowledge versus external information. It takes an LLM's internal state and a query as input, then outputs improved text generation that balances creativity with factual grounding. It's for researchers and practitioners building applications with LLMs who need to ensure high quality and trustworthy outputs.
No commits in the last 6 months.
Use this if you are working with large language models and frequently encounter issues with them producing incorrect or 'hallucinated' information, or if you need to optimize their balance between leveraging internal knowledge and retrieved data.
Not ideal if you are looking for a plug-and-play solution without any technical setup, as this project requires some familiarity with installing dependencies and setting up retrieval services.
Stars
65
Forks
8
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Oct 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/HSLiu-Initial/CtrlA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
denser-org/denser-retriever
An enterprise-grade AI retriever designed to streamline AI integration into your applications,...
rayliuca/T-Ragx
Enhancing Translation with RAG-Powered Large Language Models
neuml/rag
🚀 Retrieval Augmented Generation (RAG) with txtai. Combine search and LLMs to find insights with...
NovaSearch-Team/RAG-Retrieval
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
RulinShao/retrieval-scaling
Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".