LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
Luyao Zhuang, Qinggang Zhang, Huachi Zhou, Yujing Zhang, Xiao Huang

TL;DR
LoSemB introduces a logic-guided framework for inductive tool retrieval in large language models, effectively handling unseen tools by leveraging logical information and relational retrieval, thus overcoming limitations of existing methods.
Contribution
The paper proposes LoSemB, a novel framework that uses logic-based embeddings and relational retrieval to improve inductive tool retrieval without retraining, addressing unseen tools and distribution shifts.
Findings
Outperforms existing methods in inductive tool retrieval tasks.
Effectively handles unseen tools with logical and relational mechanisms.
Maintains strong performance in transductive settings.
Abstract
Tool learning has emerged as a promising paradigm for large language models (LLMs) to solve many real-world tasks. Nonetheless, with the tool repository rapidly expanding, it is impractical to contain all tools within the limited input length of LLMs. To alleviate these issues, researchers have explored incorporating a tool retrieval module to select the most relevant tools or represent tools as unique tokens within LLM parameters. However, most state-of-the-art methods are under transductive settings, assuming all tools have been observed during training. Such a setting deviates from reality as the real-world tool repository is evolving and incorporates new tools frequently. When dealing with these unseen tools, which refer to tools not encountered during the training phase, these methods are limited by two key issues, including the large distribution shift and the vulnerability of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Machine Learning in Materials Science · Advanced Graph Neural Networks
