让大模型决策可解释且能全局挑战，避免重复错误。
Argumentation for Explainable and Globally Contestable Decision Support with LLMs
- 构建通用决策选项的论证框架，替代单个案例推理。
- 在胶质母细胞瘤治疗推荐中实现符合临床实践的可解释建议。
- 支持对共享论证框架的修改，实现全局性争议与改进。
大型语言模型（LLMs）具备强大的通用能力，但在高风险领域部署时受限于其不透明性和不可预测性。近期研究通过基于计算论证的后验推理，为模型提供忠实解释并允许用户质疑错误决策。然而，该范式仅限于预定义的二元选择，且仅支持特定实例的局部争议，无法改变底层决策逻辑，易导致重复错误。本文提出ArgEval框架，将推理从实例特定转向结构化评估通用决策选项。不再仅针对单个案例挖掘论据，ArgEval系统地映射任务相关的决策空间，构建对应选项本体，并为每个选项建立通用论证框架（AFs）。这些框架可实例化以生成具体案例的可解释建议，同时通过修改共享的AFs支持全局争议。我们在胶质母细胞瘤治疗推荐任务中验证了ArgEval的有效性，结果表明其能生成与临床实践一致的可解释指导。
原文摘要 · Abstract (English)
Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has taken meaningful steps towards addressing these issues by augmenting LLMs with post-hoc reasoning based on computational argumentation, providing faithful explanations and enabling users to contest incorrect decisions. However, this paradigm is limited to pre-defined binary choices and only supports local contestation for specific instances, leaving the underlying decision logic unchanged and prone to repeated mistakes. In this paper, we introduce ArgEval, a framework that shifts from instance-specific reasoning to structured evaluation of general decision options. Rather than mining arguments solely for individual cases, ArgEval systematically maps task-specific decision spaces, builds corresponding option ontologies, and constructs general argumentation frameworks (AFs) for each option. These frameworks can then be instantiated to provide explainable recommendations for specific cases while still supporting global contestability through modification of the shared AFs. We investigate the effectiveness of ArgEval on treatment recommendation for glioblastoma, an aggressive brain tumour, and show that it can produce explainable guidance aligned with clinical practice.
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。