F4biian/HalluRAG
Source code of "The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States" (arXiv: https://arxiv.org/abs/2412.17056)
This project offers a specialized dataset and methodology to pinpoint 'hallucinations' in responses generated by Retrieval-Augmented Generation (RAG) applications. It takes RAG prompts and the internal processing states of Large Language Models (LLMs) as input, then identifies sentences that are ungrounded in the provided context. Data scientists and machine learning engineers working on improving the reliability of RAG systems would find this particularly useful.
No commits in the last 6 months.
Use this if you need to systematically detect and analyze when your RAG application generates inaccurate or made-up information not supported by its source materials.
Not ideal if you are looking for a general-purpose LLM hallucination detection tool outside of the RAG context or do not have access to GPU resources for running LLMs.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/F4biian/HalluRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
onestardao/WFGY
WFGY: open-source reasoning and debugging infrastructure for RAG and AI agents. Includes the...
KRLabsOrg/verbatim-rag
Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content...
iMoonLab/Hyper-RAG
"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation"...
frmoretto/clarity-gate
Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for...
project-miracl/nomiracl
NoMIRACL: A multilingual hallucination evaluation dataset to evaluate LLM robustness in RAG...