HALC
Object hallucination reducer
An implementation of an object hallucination reduction method using a PyTorch framework and various decoding algorithms.
[ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"
69 stars
3 watching
1 forks
Language: Python
last commit: 6 months ago hallucinationslarge-language-modelslvlms
Related projects:
| Repository | Description | Stars |
|---|---|---|
 lalbj/pai | Improves the performance of large language models by intervening in their internal workings to reduce hallucinations | 67 |
 junyangwang0410/haelm | A framework for detecting hallucinations in large language models | 17 |
 bradyfu/woodpecker | A method to correct hallucinations in multimodal large language models during text generation | 611 |
 amazon-science/refchecker | Automates fine-grained hallucination detection in large language model outputs | 302 |
 x-plug/mplug-halowl | Evaluates and mitigates hallucinations in multimodal large language models | 79 |
 1zhou-wang/memvr | An implementation of a method to mitigate hallucinations in large language models using visual re-tracing | 27 |
 nickjiang2378/vl-interp | This project provides an official PyTorch implementation of a method to interpret and edit vision-language representations to mitigate hallucinations in image captions. | 31 |
 damo-nlp-sg/vcd | An approach to reduce object hallucinations in large vision-language models by contrasting output distributions derived from original and distorted visual inputs | 209 |
 fuxiaoliu/lrv-instruction | A research project focused on mitigating hallucinations in large multi-modal models by improving instruction tuning through robust training methods. | 255 |
 yuqifan1117/hallucidoctor | This project provides tools and frameworks to mitigate hallucinatory toxicity in visual instruction data, allowing researchers to fine-tune MLLM models on specific datasets. | 41 |
 opendatalab/ha-dpo | A framework to improve large language model performance by mitigating hallucination effects through data and optimization techniques. | 65 |
 tianyi-lab/hallusionbench | An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy | 243 |
 assafbk/mocha_code | A unified framework and benchmark for detecting and mitigating hallucinations in open-vocabulary image captioning models | 12 |
 openkg-org/easydetect | A framework to detect and mitigate hallucinations in multimodal large language models | 48 |
 openmoss/halluqa | An evaluation framework for assessing the performance of large language models on question-answering tasks with hallucination detection | 109 |