Counterfactual-Inception
Hallucination mitigator
An implementation of a method to reduce hallucination in large multi-modal models by integrating counterfactual thinking through generated keywords.
Official PyTorch Implementation for the "What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models" paper (EMNLP Findings 2024).
15 stars
0 watching
1 forks
Language: Python
last commit: about 2 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 fuxiaoliu/lrv-instruction | A research project focused on mitigating hallucinations in large multi-modal models by improving instruction tuning through robust training methods. | 255 |
 1zhou-wang/memvr | An implementation of a method to mitigate hallucinations in large language models using visual re-tracing | 27 |
 lalbj/pai | Improves the performance of large language models by intervening in their internal workings to reduce hallucinations | 67 |
 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 |
 bradyfu/woodpecker | A method to correct hallucinations in multimodal large language models during text generation | 611 |
 assafbk/mocha_code | A unified framework and benchmark for detecting and mitigating hallucinations in open-vocabulary image captioning models | 12 |
 x-plug/mplug-halowl | Evaluates and mitigates hallucinations in multimodal large language models | 79 |
 billchan226/halc | An implementation of an object hallucination reduction method using a PyTorch framework and various decoding algorithms. | 69 |
 opendatalab/ha-dpo | A framework to improve large language model performance by mitigating hallucination effects through data and optimization techniques. | 65 |
 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 |
 junyangwang0410/haelm | A framework for detecting hallucinations in large language models | 17 |
 vectara/hallucination-leaderboard | Evaluates and compares the performance of large language models in generating hallucinations during document summarization. | 1,236 |
 yfzhang114/llava-align | Debiasing techniques to minimize hallucinations in large visual language models | 71 |
 tianyi-lab/hallusionbench | An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy | 243 |
 openkg-org/easydetect | A framework to detect and mitigate hallucinations in multimodal large language models | 48 |