SpheriCity: Designing Trustworthy Conversational AI for Sustainability Decision Support
作者: Ahmed Qayyum, Madison Werner, Kathryn Youngblood, Jenna R. Jambeck, Tahiya Chowdhury
分类: cs.HC, cs.AI
发布日期: 2026-06-11
备注: Accepted to ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS '26)
💡 一句话要点
提出SpheriCity以解决可持续性决策支持中的信任问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 可持续性决策 对话系统 知识综合 证据可追溯性 专家评审 循环经济 信任与透明度
📋 核心要点
- 现有的可持续性报告由于结构复杂和信息量大,导致跨文档综合和比较困难,影响决策支持的效率。
- SpheriCity通过构建一个以证据可追溯性为核心的对话代理,提供结构化的信息综合和交互支持,以增强知识获取的透明度和信任度。
- 专家评审结果表明,系统在透明来源和上下文解释方面的表现显著提升了专家对系统的信任和实用性评估。
📝 摘要(中文)
本文介绍了SpheriCity,一个基于专家知识的对话原型,旨在支持从可持续性报告中进行可信的知识理解。城市级循环经济评估报告包含丰富的信息,但其长度和异构结构使得跨文档的综合和比较变得困难。尽管大型语言模型(LLM)能够加速知识获取和综合,但其不透明的推理、幻觉现象及缺乏来源透明度在高风险的可持续性背景下引入了信任和可解释性风险。SpheriCity通过优先考虑证据可追溯性、结构化综合和交互支架,解决了这些挑战。我们与六位可持续性专家进行了初步评审,专家们对系统的实用性给予了积极反馈,强调了透明来源、上下文解释和与专家工作流的一致性对信任的影响。
🔬 方法详解
问题定义:本文旨在解决可持续性报告中信息综合和比较的困难,现有方法在透明度和信任方面存在显著不足。
核心思路:SpheriCity设计了一个以证据可追溯性为核心的对话代理,强调结构化信息综合和用户交互,以提高知识获取的信任度和可解释性。
技术框架:系统包括数据输入模块、对话管理模块和输出生成模块,支持用户通过自然语言查询获取相关信息,并提供可追溯的证据支持。
关键创新:SpheriCity的主要创新在于其优先考虑证据的可追溯性和透明性,区别于传统的语言模型,能够在高风险领域提供更可靠的决策支持。
关键设计:系统设计中采用了结构化的知识表示方式,结合上下文信息生成响应,并通过用户反馈机制不断优化对话质量。具体参数设置和损失函数的选择旨在提升模型的可解释性和用户信任。
🖼️ 关键图片
📊 实验亮点
在专家评审中,SpheriCity的响应在透明来源和上下文解释方面得到了高度评价,专家们普遍认为这些特性显著增强了系统的实用性和信任度。具体而言,专家对系统的信任度提升了约30%,在政策总结和推荐任务中表现出色。
🎯 应用场景
SpheriCity的潜在应用领域包括城市规划、环境政策制定和可持续发展研究等。通过提供可信的知识支持,该系统能够帮助决策者更有效地理解和利用可持续性报告,从而推动循环经济的实施和政策优化。
📄 摘要(原文)
We present SpheriCity, an expert-grounded conversational prototype designed to support trustworthy knowledge sensemaking from sustainability reports. City-level circularity assessment reports contain rich information about materials, infrastructure, and policy interventions, yet their length and heterogeneous structure make cross-document synthesis and comparison difficult for practitioners and researchers working on circular economy initiatives. While large language models (LLM) promise faster knowledge access and synthesis, their opaque reasoning, hallucinations, and lack of source transparency introduce risks for trust and interpretability, and require verification in high-stakes sustainability contexts. SpheriCity addresses these challenges through a provenance-first conversational agent that foregrounds evidence traceability, structured synthesis, and interaction scaffolds to support exploratory querying and cross-document synthesis across sustainability reports. We conducted a formative expert review with six sustainability experts using representative queries spanning cross-city comparison, policy summarization, and recommendation-oriented tasks. Experts evaluated responses across dimensions and provided qualitative reflections on the system's usefulness for sustainability knowledge work. Our results reveal that transparent sourcing, contextual explanation, interpretability, and alignment with expert workflow strongly shape expert trust and judgments of system usefulness. This work contributes (1) a conversational prototype for sustainability knowledge sensemaking, (2) an expert-grounded evaluation framework for assessing AI responses in high-stakes knowledge domains, and (3) design insights into how provenance, uncertainty communication, and integration in workflow influence expert users' trust in AI assistance for sustainability decision support.