Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models
Keywords: Large Language Models, Medication Consultation, Retrieval-Augmented Generation, Tool Call
TL;DR: This study introduces a benchmark containing multi-round dialogues for medication consultation and a novel retrieval-augmented framework with the tool calling mechanism.
Abstract: Large-scale language models (LLMs) have achieved remarkable success across various language tasks but suffer from hallucinations and temporal misalignment. To mitigate these shortcomings, Retrieval-augmented generation (RAG) has been utilized to provide external knowledge to facilitate the answer generation. However, applying such models to the medical domain faces several challenges due to the lack of domain-specific knowledge and the intricacy of real-world scenarios.
In this study, we explore LLMs with RAG framework for knowledge-intensive tasks in the medical field. To evaluate the capabilities of LLMs, we introduce MedicineQA, a multi-round dialogue benchmark that simulates the real-world medication consultation scenario and requires LLMs to answer with retrieved evidence from the medicine database. MedicineQA contains 300 multi-round question-answering pairs, each embedded within a detailed dialogue history, highlighting the challenge posed by this knowledge-intensive task to current LLMs. We further propose a new \textit{Distill-Retrieve-Read} framework instead of the previous \textit{Retrieve-then-Read}. Specifically, the distillation and retrieval process utilizes a tool calling mechanism to formulate search queries that emulate the keyword-based inquiries used by search engines. With experimental results, we show that our framework brings notable performance improvements and surpasses the previous counterparts in the evidence retrieval process in terms of evidence retrieval accuracy. This advancement underscores the framework's potential to effectively address the inherent challenges of applying RAG models to the medical domain.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 708
Loading