构建面向自动驾驶的多模态知识编辑数据集，提升模型对交通知识的精准调整能力。
ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems
- 设计多模态数据集，支持对自动驾驶模型进行精准知识修改。
- 涵盖真实场景、多类型数据与全面评估指标，验证编辑效果。
- 适合研究自动驾驶知识更新与模型可解释性的研究人员。
大型多模态模型（LMMs）在自动驾驶系统（ADS）中展现出巨大潜力，但其直接应用受限于对交通知识的理解偏差、复杂道路环境及车辆状态多样性等问题。为此，我们提出采用知识编辑技术，实现无需全量重训练即可针对性调整模型行为。同时，我们构建了专用于自动驾驶的多模态知识编辑数据集 ADS-Edit，包含多种真实世界场景、多类数据模态及完整的评估指标。通过大量实验，我们获得若干有意义的发现。希望本工作能推动知识编辑在自动驾驶领域的进一步发展。代码与数据已公开于 https://github.com/zjunlp/EasyEdit/blob/main/examples/ADSEdit.md。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。