基于LLM的金融教育问答角色感知多智能体框架
A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs
AI总结：
本文提出一个基于角色提示的多智能体框架，通过Base Generator、Evidence Retriever和Expert Reviewer协同单次迭代，利用RAG和专家审查提升金融教育QA性能，准确率较零样本CoT基线提高6.6-8.3%，使小模型媲美金融微调大模型。
摘要：
问答（QA）在金融教育中发挥着核心作用，然而现有的LLM方法往往无法捕捉金融问题解决所需的细致专业推理。金融领域需要多步定量推理、熟悉领域特定术语以及理解现实场景。我们提出了一个多智能体框架，利用基于角色的提示来提升领域特定QA的性能。该框架包含Base Generator、Evidence Retriever和Expert Reviewer智能体，通过单次迭代协同生成精炼答案。我们在在线学习平台Study.com的3,532个专家设计的金融教育问题上评估了该框架。我们利用检索增强生成（RAG）从6本金融教科书中获取上下文证据，并采用提示策略实现领域专家审查。实验表明，基于批评的精炼将答案准确率比零样本思维链基线提高了6.6-8.3%，其中Gemini-2.0-Flash表现最佳。此外，我们的方法使GPT-4o-mini达到了与金融微调的FinGPT-mt_Llama3-8B_LoRA相当的性能。结果表明这是一种增强金融QA的经济有效方法，为多智能体金融LLM系统的进一步研究提供了见解。
英文摘要：
Question answering (QA) plays a central role in financial education, yet existing large language model (LLM) approaches often fail to capture the nuanced and specialized reasoning required for financial problem-solving. The financial domain demands multistep quantitative reasoning, familiarity with domain-specific terminology, and comprehension of real-world scenarios. We present a multi-agent framework that leverages role-based prompting to enhance performance on domain-specific QA. Our framework comprises a Base Generator, an Evidence Retriever, and an Expert Reviewer agent that work in a single-pass iteration to produce a refined answer. We evaluated our framework on a set of 3,532 expert-designed finance education questions from Study.com, an online learning platform. We leverage retrieval-augmented generation (RAG) for contextual evidence from 6 finance textbooks and prompting strategies for a domain-expert reviewer. Our experiments indicate that critique-based refinement improves answer accuracy by 6.6-8.3% over zero-shot Chain-of-Thought baselines, with the highest performance from Gemini-2.0-Flash. Furthermore, our method enables GPT-4o-mini to achieve performance comparable to the finance-tuned FinGPT-mt_Llama3-8B_LoRA. Our results show a cost-effective approach to enhancing financial QA and offer insights for further research in multi-agent financial LLM systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
