HA-DPO
by opendatalab
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
AI summary
Hallucination fixer
A framework to improve large language model performance by mitigating hallucination effects through data and optimization techniques.
- stars
- 73
- forks
- 6
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
Hallucination fixer
An implementation of a method to mitigate hallucinations in large language models using visual re-tracing
Hallucination fixer
Improves the performance of large language models by intervening in their internal workings to reduce hallucinations
Hallucination corrector
A method to correct hallucinations in multimodal large language models without requiring retraining
Data processing framework
This project provides tools and frameworks to mitigate hallucinatory toxicity in visual instruction data, allowing researchers to fine-tune MLLM models on specific datasets.
Hallucination detector
An evaluation framework for assessing the performance of large language models on question-answering tasks with hallucination detection
Hallucination detector
A framework to detect and mitigate hallucinations in multimodal large language models
Hallucination detector
A framework for detecting hallucinations in large language models
Hallucination mitigation
A research project focused on mitigating hallucinations in large multi-modal models by improving instruction tuning through robust training methods.
Object hallucination reducer
An implementation of an object hallucination reduction method using a PyTorch framework and various decoding algorithms.
Hallucination tester
Evaluates and mitigates hallucinations in multimodal large language models
Object detection method
An approach to reduce object hallucinations in large vision-language models by contrasting output distributions derived from original and distorted visual inputs
Model debiasing
Debiasing techniques to minimize hallucinations in large visual language models
Hallucination detection and mitigation
A unified framework and benchmark for detecting and mitigating hallucinations in open-vocabulary image captioning models
Hallucination Detector
Automates fine-grained hallucination detection in large language model outputs
Benchmark
An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy
