arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.12583cs.CLcs.AI
收藏

STRUX:一种基于结构化解释的决策LLM

STRUX: An LLM for Decision-Making with Structured Explanations

Emory University(埃默里大学);University of Central Florida(中佛罗里达大学)

Yiming Lu, Yebowen Hu, Hassan Foroosh, Wei Jin, Fei Liu

AI总结:

本文提出 STRUX 框架,通过将信息提炼为关键事实表并自我反思分类为有利或不利因素,微调 LLM 生成结构化解释以优化决策,在股票投资预测任务中超越基线并提升透明度。

摘要:

无数决策塑造了我们的日常生活,理解这些选择背后的如何与为何至关重要。本文提出了一种名为 STRUX 的新 LLM 决策框架,通过提供结构化解释来增强 LLM 决策。这些解释包含与决策相关的有利和不利事实及其各自强度。STRUX 首先将冗长信息提炼为关键事实简表,随后通过一系列自我反思步骤确定哪些事实具有关键性,并针对特定决策将其归类为有利或不利。最后,我们对 LLM 进行微调,以识别并优先处理这些关键事实,从而优化决策。STRUX 在基于财报电话会议记录预测股票投资决策这一挑战性任务上进行了评估,相较于强基线展现出卓越性能。它允许用户理解不同因素的影响,提升了决策透明度,标志着向 LLM 实用决策迈出了重要一步。

英文摘要:

Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework called STRUX, which enhances LLM decision-making by providing structured explanations. These include favorable and adverse facts related to the decision, along with their respective strengths. STRUX begins by distilling lengthy information into a concise table of key facts. It then employs a series of self-reflection steps to determine which of these facts are pivotal, categorizing them as either favorable or adverse in relation to a specific decision. Lastly, we fine-tune an LLM to identify and prioritize these key facts to optimize decision-making. STRUX has been evaluated on the challenging task of forecasting stock investment decisions based on earnings call transcripts and demonstrated superior performance against strong baselines. It enhances decision transparency by allowing users to understand the impact of different factors, representing a meaningful step towards practical decision-making with LLMs.

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。

↑