mala-lab/HaMI
[NeurIPS 2025] Official implementation for ''Robust Hallucination Detection in LLMs via Adaptive Token Selection'' https://arxiv.org/abs/2504.07863
This project helps ensure the accuracy of responses from large language models (LLMs) by detecting when they generate incorrect or made-up information, known as 'hallucinations.' It takes the LLM's generated text and identifies specific parts that are untruthful, providing a reliable check on the output. Anyone building or using LLM-powered applications, especially in sensitive domains, would benefit from this to maintain trustworthiness.
Use this if you need a robust way to automatically identify and flag 'hallucinations' in the text generated by your large language models, especially across diverse types of questions and answers.
Not ideal if you are looking for a tool that generates content or focuses on general LLM performance metrics rather than specifically targeting truthfulness and factual accuracy.
Stars
11
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mala-lab/HaMI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
THU-BPM/MarkLLM
MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 System Demonstration)
git-disl/Vaccine
This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large...
zjunlp/Deco
[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
HillZhang1999/ICD
Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced...
voidism/DoLa
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality...