BillChan226/HALC
[ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"
When working with AI models that describe images, sometimes they "hallucinate" objects that aren't actually present in the picture. This project helps reduce those misleading descriptions. You input an image and a visual language model's generated caption, and it outputs a more accurate caption by identifying and removing any objects the model incorrectly imagined. This is designed for AI researchers and practitioners who build or use visual language models and need to ensure their descriptions are factually correct.
110 stars. No commits in the last 6 months.
Use this if you need to make sure your visual language models provide accurate descriptions of images, free from imagined objects.
Not ideal if you are looking for a tool to generate initial image captions rather than refine existing ones for factual accuracy.
Stars
110
Forks
4
Language
Python
License
MIT
Category
Last pushed
Dec 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/BillChan226/HALC"
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...