[2025]

@inproceedings{Li2025d,

title = {Multi-PrefDrive: Optimizing Large Language Models for Autonomous Driving Through Multi-Preference Tuning},

author = {Yun Li and Ehsan Javanmardi and Simon Thompson and Kai Katsumata and Alex Orsholits and Manabu Tsukada},

url = {https://liyun0607.github.io/},

doi = {10.1109/IROS60139.2025.11247608},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},

address = {Hangzhou, China},

abstract = {This paper introduces Multi-PrefDrive, a framework that significantly enhances LLM-based autonomous driving through multidimensional preference tuning. Aligning LLMs with human driving preferences is crucial yet challenging, as driving scenarios involve complex decisions where multiple incorrect actions can correspond to a single correct choice. Traditional binary preference tuning fails to capture this complexity. Our approach pairs each chosen action with multiple rejected alternatives, better reflecting real-world driving decisions. By implementing the Plackett-Luce preference model, we enable nuanced ranking of actions across the spectrum of possible errors. Experiments in the CARLA simulator demonstrate that our algorithm achieves an 11.0% improvement in overall score and an 83.6% reduction in

infrastructure collisions, while showing perfect compliance with traffic signals in certain environments. Comparative analysis against DPO and its variants reveals that Multi-PrefDrive’s superior discrimination between chosen and rejected actions, which achieving a margin value of 25, and such ability has been directly translates to enhanced driving performance. We implement memory-efficient techniques including LoRA and 4-bit quantization to enable deployment on consumer-grade hardware and will open-source our training code and multi-rejected dataset to advance research in LLM-based autonomous driving systems. Project Page (https://liyun0607.github.io/)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2025c,

title = {PrefDrive: Enhancing Autonomous Driving through Preference-Guided Large Language Models},

author = {Yun Li and Ehsan Javanmardi and Simon Thompson and Kai Katsumata and Alex Orsholits and Manabu Tsukada},

url = {https://github.com/LiYun0607/PrefDrive/

https://huggingface.co/liyun0607/PrefDrive

https://huggingface.co/datasets/liyun0607/PrefDrive},

doi = {10.1109/IV64158.2025.11097672},

year  = {2025},

date = {2025-06-22},

urldate = {2025-06-22},

booktitle = {36th IEEE Intelligent Vehicles Symposium (IV2025)},

address = {Cluj-Napoca, Romania},

abstract = {This paper presents PrefDrive, a novel framework that integrates driving preferences into autonomous driving models through large language models (LLMs). While recent advances in LLMs have shown promise in autonomous driving, existing approaches often struggle to align with specific driving behaviors (e.g., maintaining safe distances, smooth acceleration patterns) and operational requirements (e.g., traffic rule compliance, route adherence). We address this challenge by developing a preference learning framework that combines multimodal perception with natural language understanding. Our approach leverages Direct Preference Optimization (DPO) to fine-tune LLMs efficiently on consumer-grade hardware, making advanced autonomous driving research more accessible to the broader research community. We introduce a comprehensive dataset of 74,040 sequences, carefully annotated with driving preferences and driving decisions, which, along with our trained model checkpoints, will be made publicly available to facilitate future research. Through extensive experiments in the CARLA simulator, we demonstrate that our preference-guided approach significantly improves driving performance across multiple metrics, including distance maintenance and trajectory smoothness. Results show up to 28.1% reduction in traffic rule violations and 8.5% improvement in navigation task completion while maintaining appropriate distances from obstacles. The framework demonstrates robust performance across different urban environments, showcasing the effectiveness of preference learning in autonomous driving applications.  },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}