Qingyu Yin

Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models trained on open-source IFT datasets only have the ability to follow instructions from users, and often fail to follow complex role and rules specified by developers, a.k.a. system prompts.

1. Introduction With the vigorous development of China’s new energy vehicle industry, the construction of charging infrastructure has become the focus of attention. Among them, the “supercharging” mode, represented by DC fast-charging technology, provides users with a convenient charging experience due to its efficient and fast charging speed, and has become one of the important development directions of the global new energy vehicle industry.

Understanding user intentions is essential for improving product recommendations, navigation suggestions, and query reformula-tions. However, user intentions can be intricate, involving multiple sessions and attribute requirements connected by logical operators such as And, Or, and Not. For instance, a user may search for Nike or Adidas running shoes across various sessions, with a preference for purple.