HillZhang1999/ICD
Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"
This project helps AI developers and researchers improve the factual accuracy of their large language models (LLMs). It takes an existing LLM that sometimes generates incorrect information and applies a decoding strategy to reduce 'hallucinations'. The output is a more truthful LLM that can produce content with fewer factual errors, suitable for applications where accuracy is critical.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher trying to reduce factual errors in the text generated by your large language models, especially open-source models like Llama2-7B-Chat or Mistral-7B-Instruct.
Not ideal if you need a solution for models other than large language models, or if you're not comfortable working with model decoding strategies and command-line scripts.
Stars
69
Forks
10
Language
Python
License
MIT
Category
Last pushed
Feb 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HillZhang1999/ICD"
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
voidism/DoLa
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality...
kaist-cvml/I-HallA-v1.0
[AAAI 2025] Official Implementation of I-HallA v1.0