SpheriCity: Designing Trustworthy Conversational AI for Sustainability Decision Support

2026-06-11

AI Summary

This study addresses the challenges posed by structurally heterogeneous and verbose urban circular economy assessment reports, which impede cross-document knowledge integration, and the limitations of general-purpose large language models (LLMs) in high-stakes sustainability decision-making due to opaque reasoning and hallucination risks. To bridge this gap, the authors propose SpheriCity—the first expert-driven conversational system tailored for sustainable knowledge work—that synergistically integrates LLMs with domain expertise. SpheriCity enables traceable and verifiable knowledge synthesis through evidence provenance tracking, structured information extraction, context-aware explanatory generation, and interactive guidance. Evaluated by six domain experts, the system demonstrates strong performance in cross-city comparisons, policy summarization, and recommendation generation, with its transparent sourcing, interpretability, and workflow alignment significantly enhancing expert trust and willingness to adopt AI assistance.

Abstract

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.

Problem

• sustainability decision support
• circular economy
• trustworthy AI
• knowledge synthesis
• large language models

Innovation

• provenance-first
• conversational AI
• sustainability decision support
• evidence traceability
• expert-grounded evaluation