让AI根据价值观做个性化决策，更贴近人类判断。
ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making
- 分两阶段生成价值场景并训练决策模型
- 在多种价值维度下决策准确率超越主流大模型
- 适合研究可解释性与个性化AI的学者
尽管人工智能取得进展，但在未涵盖于训练数据的任务中仍难以保证个性化决策。为此，我们提出ValuePilot，一个包含数据集生成工具DGT和决策模块DMM的两阶段价值驱动决策框架。DGT基于价值维度生成场景，结合自动化过滤与人工校验，确保数据真实性；在生成的数据集上，DMM学习识别场景内在价值，评估行动可行性，并权衡多维价值做出个性化决策。大量实验表明，在给定人类价值偏好时，该框架的决策最接近人类判断，优于Claude-3.5-Sonnet、Gemini-2-flash、Llama-3.1-405b和GPT-4o。本研究为价值驱动决策提供初步探索，旨在激发学界对价值驱动与个性化决策的关注。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。