发表机构
Gonzaga University; Cardiff University; University of Illinois Urbana-Champaign（贡萨加大学; 卡迪夫大学; 伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ABDA-NL通过自然语言界面扩展了基于论证的推理系统，利用大型语言模型连接语言与形式化，同时保持确定性引擎作为论证和接受标签的唯一来源，支持交互式探索和用户验证。
AI 中文摘要
ABDA-NL为ABDA添加了一个自然语言界面，ABDA是一个使用ASPIC-知识库在基础语义下进行基于论证讨论的系统。用户可以看到哪些结论被接受、拒绝或未定，打开交互式的基础讨论游戏渲染以了解原因，通过暂停假设和规则或更改偏好来探索假设性替代方案，提出从场景参考文档中回答的问题，并用简单的英语编写新的事实、假设和规则。大型语言模型提供了语言与形式主义之间的桥梁：它回答来自文档和场景当前状态的问题，并将纯英语编辑转换为候选形式陈述。确定性的ABDA引擎仍然是论点、攻击和接受标签的唯一来源，并且模型的每个提议在生效前都由用户验证和确认。
英文摘要
ABDA-NL adds a natural-language interface to ABDA, a system for argument-based discussion using ASPIC- knowledge bases under grounded semantics. Users see which conclusions are accepted, rejected, or undecided, open an interactive rendering of the grounded discussion game to learn why, explore what-if alternatives by suspending assumptions and rules or changing preferences, ask questions that are answered from a scenario's reference documents, and author new facts, assumptions, and rules in plain English. A large language model provides the bridge between language and formalism: it answers questions from the documents and the current state of the scenario, and it translates plain-English edits into candidate formal statements. The deterministic ABDA engine remains the sole source of arguments, attacks, and acceptance labels, and every proposal of the model is validated and confirmed by the user before it takes effect.
Comments9 pages, 3 figures. Extended version of a demonstration abstract in the Proceedings of COMMA 2026. Code at https://github.com/idaks/ABDA-NL and live demo at https://demo.abda-nl.org
