让AI与人辩论式决策，而非单方面给出答案。
Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us
- 用论证框架挖掘与合成技术融合LLM的文本理解能力
- 实现可争议、可修改的动态决策过程，非固定结论输出
- 适合医疗、司法等需可信推理的高风险场景
计算论证提供了透明、可验证的推理框架，但传统方法依赖领域特定信息且需大量特征工程。相比之下，大语言模型擅长处理非结构化文本，却因黑箱特性难以评估与信任。我们提出，二者融合将催生新范式：论辩式人机决策。通过论证框架挖掘、合成与论辩推理的协同，使AI不仅解释决策，更能与人类展开对话式推理，使决策具备可争议性和可修订性——真正与人共同思考，而非替人做决定。该融合对高风险领域中以人为本、值得信赖的AI至关重要。
原文摘要 · Abstract (English)
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.
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。