PAI

Hallucination fixer

Improves the performance of large language models by intervening in their internal workings to reduce hallucinations

[ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

GitHub

83 stars
2 watching
3 forks
Language: Python
last commit: about 1 month ago

Related projects:

Repository Description Stars
1zhou-wang/memvr An implementation of a method to mitigate hallucinations in large language models using visual re-tracing 28
bradyfu/woodpecker A method to correct hallucinations in multimodal large language models without requiring retraining 617
opendatalab/ha-dpo A framework to improve large language model performance by mitigating hallucination effects through data and optimization techniques. 73
billchan226/halc An implementation of an object hallucination reduction method using a PyTorch framework and various decoding algorithms. 72
fuxiaoliu/lrv-instruction A research project focused on mitigating hallucinations in large multi-modal models by improving instruction tuning through robust training methods. 262
yfzhang114/llava-align Debiasing techniques to minimize hallucinations in large visual language models 75
x-plug/mplug-halowl Evaluates and mitigates hallucinations in multimodal large language models 82
amazon-science/refchecker Automates fine-grained hallucination detection in large language model outputs 325
tianyi-lab/hallusionbench An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy 259
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. 46
junyangwang0410/haelm A framework for detecting hallucinations in large language models 17
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
assafbk/mocha_code A unified framework and benchmark for detecting and mitigating hallucinations in open-vocabulary image captioning models 13
bcdnlp/faithscore Evaluates answers generated by large vision-language models to assess hallucinations 27
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 222