arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.15946cs.AI
收藏

论证型人机决策:迈向与我们共思而非为我们决策的AI代理

Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us

New Mexico State University(新墨西哥州立大学);King's College London(伦敦国王学院);Imperial College London(伦敦帝国学院);Washington University in St. Louis(圣路易斯华盛顿大学)

Stylianos Loukas Vasileiou, Antonio Rago, Francesca Toni, William Yeoh

AI总结:

本文探讨论证型人机决策的新范式,结合论证框架挖掘、合成与推理,使AI代理能与人类进行辩证互动,提升高风险领域的人工智能可信度。

摘要:

计算论证提供了透明且可验证的推理框架,但传统上受限于领域特定信息和大量特征工程。相比之下,LLM在处理非结构化文本方面表现优异,但其不透明性使推理难以评估和信任。我们主张这两个领域的融合将奠定新范式:论证型人机决策。我们分析论证框架挖掘、合成和推理的协同作用,使代理不仅能够解释决策,还能进行辩证过程,使决策可挑战和修订——与人类共思而非为人类决策。计算论证与LLM的融合对于高风险领域的人工智能可信度至关重要。

英文摘要:

Computational argumentation offers formal frameworks for transparent, verifiable reasoning but has traditionally been limited by its reliance on domain-specific information and extensive feature engineering. In contrast, LLMs excel at processing unstructured text, yet their opaque nature makes their reasoning difficult to evaluate and trust. We argue that the convergence of these fields will lay the foundation for a new paradigm: Argumentative Human-AI Decision-Making. We analyze how the synergy of argumentation framework mining, argumentation framework synthesis, and argumentative reasoning enables agents that do not just justify decisions, but engage in dialectical processes where decisions are contestable and revisable -- reasoning with humans rather than for them. This convergence of computational argumentation and LLMs is essential for human-aware, trustworthy AI in high-stakes domains.

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。

↑