arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.19633cs.AIcs.CE
收藏

时间序列增强生成用于金融应用

Time Series Augmented Generation for Financial Applications

SingularityNET Foundation(SingularityNET基金会)

Anton Kolonin, Alexey Glushchenko, Evgeny Bochkov, Abhishek Saxena

AI总结:

本文提出了一种新的评估方法和基准,用于衡量LLM在金融时间序列分析中的推理能力,通过大规模实证研究验证了工具增强范式的有效性。

摘要:

评估大型语言模型(LLM)在复杂定量金融任务中的推理能力是一个关键且未解决的挑战。标准基准往往无法隔离代理解析查询和协调计算的核心能力。为此,我们引入了一种新的评估方法和基准,旨在严格测量LLM代理在金融时间序列分析中的推理能力。我们应用这种方法在大规模实证研究中使用我们的框架Time Series Augmented Generation(TSAG),其中LLM代理将定量任务委托给可验证的外部工具。我们的基准由100个金融问题组成,用于比较多个最先进的代理(如GPT-4o、Llama 3、Qwen2)在评估工具选择准确性、忠实性和幻觉的指标上。结果表明,有能力的代理可以实现接近完美的工具使用准确性,同时最小化幻觉,验证了工具增强范式。我们的主要贡献是这一评估框架和相应的代理性能实证洞察,我们将其公开发布,以促进标准化的可靠金融AI研究。

英文摘要:

Evaluating the reasoning capabilities of Large Language Models (LLMs) for complex, quantitative financial tasks is a critical and unsolved challenge. Standard benchmarks often fail to isolate an agent's core ability to parse queries and orchestrate computations. To address this, we introduce a novel evaluation methodology and benchmark designed to rigorously measure an LLM agent's reasoning for financial time-series analysis. We apply this methodology in a large-scale empirical study using our framework, Time Series Augmented Generation (TSAG), where an LLM agent delegates quantitative tasks to verifiable, external tools. Our benchmark, consisting of 100 financial questions, is used to compare multiple SOTA agents (e.g., GPT-4o, Llama 3, Qwen2) on metrics assessing tool selection accuracy, faithfulness, and hallucination. The results demonstrate that capable agents can achieve near-perfect tool-use accuracy with minimal hallucination, validating the tool-augmented paradigm. Our primary contribution is this evaluation framework and the corresponding empirical insights into agent performance, which we release publicly to foster standardized research on reliable financial AI.

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。

↑