ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems
This work addresses the problem of adapting AI models for autonomous driving by providing a dataset and method for targeted knowledge editing, which is incremental as it builds on existing knowledge editing techniques.
The paper tackles the challenge of applying Large Multimodal Models to Autonomous Driving Systems by proposing Knowledge Editing to avoid full retraining, and introduces ADS-Edit, a multimodal dataset with real-world scenarios and evaluation metrics to support this approach.
Recent advancements in Large Multimodal Models (LMMs) have shown promise in Autonomous Driving Systems (ADS). However, their direct application to ADS is hindered by challenges such as misunderstanding of traffic knowledge, complex road conditions, and diverse states of vehicle. To address these challenges, we propose the use of Knowledge Editing, which enables targeted modifications to a model's behavior without the need for full retraining. Meanwhile, we introduce ADS-Edit, a multimodal knowledge editing dataset specifically designed for ADS, which includes various real-world scenarios, multiple data types, and comprehensive evaluation metrics. We conduct comprehensive experiments and derive several interesting conclusions. We hope that our work will contribute to the further advancement of knowledge editing applications in the field of autonomous driving. Code and data are available in https://github.com/zjunlp/EasyEdit/blob/main/examples/ADSEdit.md.