UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

[NeurIPS 2025] SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

RAG Hallucination Detecting By LRP.

Build your own open-source REST API endpoint to detect hallucination in LLM generated responses.

Splinfer is an inference layer built with llama.cpp that helps to better understand uncertainty during generation and hallucination probability.

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

This repository contains the codebase for the PoC of LLM package hallucination and associated vulnerabilties.