paper-with-me

홈 › Papers

Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graph

2025-06-26 · Jingwei Wang, Zai Zhang, Hao Qian, Chunjing Gan, Binbin Hu, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Bin Shi, Bo Dong

Teaching large language models (LLMs) to use tools is crucial for improving their problem-solving abilities and expanding their applications. However, effectively using tools is challenging because it requires a deep understanding of tool functionalities and user intentions. Previous methods relied mainly on LLMs to generate instruction data, but the quality of these data was often insufficient. In this paper, we propose a new method that uses knowledge graphs to generate high-quality instruction data for LLMs. Knowledge graphs are manually curated datasets rich in semantic information. We begin by extracting various query pathways from a given knowledge graph, which are transformed into a broad spectrum of user queries. We then translate the relationships between entities into actionable tools and parse the pathways of each query into detailed solution steps, thereby creating high-quality instruction data. Our experiments show that fine-tuning on just a small sample of this synthetic data can significantly improve the tool utilization and overall capabilities of LLMs.

📄 PDF Abstract BibTeX arXiv:2506.21071

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

Self-Review Framework for Enhancing Instruction Following Capability of LLM

2025-07-08 · Sihyun Park arxiv

Various techniques have been proposed to improve large language models (LLMs) adherence to formatting and instruction constraints. One of the most effective approaches involves utilizing high-quality data generated by po…

Instruction Following

Importance-Aware Data Selection for Efficient LLM Instruction Tuning

2025-11-10 · Tingyu Jiang, Shen Li, Yiyao Song, Lan Zhang 외 arxiv

Instruction tuning plays a critical role in enhancing the performance and efficiency of Large Language Models (LLMs). Its success depends not only on the quality of the instruction data but also on the inherent capabilit…

SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation

2025-02-07 · Jungwoo Kim, Minsang Kim, Sungjin Lee

The rapid evolution of Large Language Models (LLMs) has enabled the industry to develop various AI-based services. Instruction tuning is considered essential in adapting foundation models for target domains to provide hi…

Diversity

ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix

2025-10-27 · Zile Yang, Ling Li, Na Di, Jinlong Pang 외 arxiv

Supervised Fine-Tuning (SFT) adapts pre-trained Large Language Models (LLMs) to domain-specific instructions by training on a carefully curated subset of high-quality instruction-response pairs, typically drawn from a la…

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

2025-07-31 · Mingzhe Li, Xin Lu, Yanyan Zhao arxiv

Synthesizing high-quality instruction data from unsupervised text is a promising paradigm for training large language models (LLMs), yet automated methods for this task still exhibit significant limitations in the divers…