arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04569cs.AI
收藏

ValuePilot:一个价值驱动的决策制定两阶段框架

ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

BIGAI(北京智源人工智能研究院);Tsinghua University(清华大学)

Yitong Luo, Hou Hei Lam, Ziang Chen, Zhenliang Zhang, Xue Feng

AI总结:

提出两阶段价值驱动决策框架ValuePilot,通过DGT生成数据集并训练DMM模块,在给定人类价值偏好下实现最接近人类的个性化决策,优于多个主流大模型。

摘要:

尽管人工智能(AI)近期取得了进展,但在训练数据集中未考虑的任务中确保个性化决策制定仍面临挑战。为了解决这个问题,我们提出了ValuePilot,这是一个两阶段价值驱动的决策制定框架,包含数据集生成工具包DGT和基于生成数据训练的决策制定模块DMM。DGT能够基于价值维度生成场景并紧密反映现实世界任务,通过自动过滤技术和人工筛选来确保数据集的有效性。在生成的数据集中,DMM学习识别场景的内在价值,计算行动可行性,并在多个价值维度之间权衡以做出个性化决策。大量实验表明,在给定人类价值偏好的情况下,我们的DMM最接近人类决策,优于Claude-3.5-Sonnet、Gemini-2-flash、Llama-3.1-405b和GPT-4o。这项研究是价值驱动决策制定的初步探索。我们希望它能激发社区对价值驱动决策制定和个性化决策制定的兴趣。

英文摘要:

Despite recent advances in artificial intelligence (AI), it poses challenges to ensure personalized decision-making in tasks that are not considered in training datasets. To address this issue, we propose ValuePilot, a two-phase value-driven decision-making framework comprising a dataset generation toolkit DGT and a decision-making module DMM trained on the generated data. DGT is capable of generating scenarios based on value dimensions and closely mirroring real-world tasks, with automated filtering techniques and human curation to ensure the validity of the dataset. In the generated dataset, DMM learns to recognize the inherent values of scenarios, computes action feasibility and navigates the trade-offs between multiple value dimensions to make personalized decisions. Extensive experiments demonstrate that, given human value preferences, our DMM most closely aligns with human decisions, outperforming Claude-3.5-Sonnet, Gemini-2-flash, Llama-3.1-405b and GPT-4o. This research is a preliminary exploration of value-driven decision-making. We hope it will stimulate interest in value-driven decision-making and personalized decision-making within the community.

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。

↑