{"type":"ScholarlyArticle","title":"LogiDebrief: A Signal-Temporal Logic Based Automated Debriefing Approach with Large Language Models Integration","authors":[{"name":"Zirong Chen","slug":"zirong-chen","given":"Zirong","family":"Chen","affiliation":""},{"name":"Ziyan An","slug":"ziyan-an","given":"Ziyan","family":"An","affiliation":""},{"name":"Jennifer Reynolds","slug":"jennifer-reynolds","given":"Jennifer","family":"Reynolds","affiliation":""},{"name":"Kristin Mullen","slug":"kristin-mullen","given":"Kristin","family":"Mullen","affiliation":""},{"name":"Stephen Maritini","slug":"stephen-maritini","given":"Stephen","family":"Maritini","affiliation":""},{"name":"Meiyi Ma","slug":"meiyi-ma","given":"Meiyi","family":"Ma","affiliation":""}],"abstract":"Emergency response services are critical to public safety, with 9-1-1 call-takers playing a key role in ensuring timely and effective emergency operations. To ensure call-taking performance consistency, quality assurance is implemented to evaluate and refine call-takers' skillsets. However, traditional human-led evaluations struggle with high call volumes, leading to low coverage and delayed assessments.  We introduce LogiDebrief, an AI-driven framework that automates traditional 9-1-1 call debriefing by integrating Signal-Temporal Logic (STL) with Large Language Models (LLMs) for fully-covered rigorous performance evaluation. LogiDebrief formalizes call-taking requirements as logical specifications, enabling systematic assessment of 9-1-1 calls against procedural guidelines. It employs a three-step verification process: (1) contextual understanding to identify responder types, incident classifications, and critical conditions; (2) STL-based runtime checking with LLM integration to ensure compliance; and (3) automated aggregation of results into quality assurance reports.  Beyond its technical contributions, LogiDebrief has demonstrated real-world impact. Successfully deployed at Metro Nashville Department of Emergency Communications, it has assisted in debriefing 1,701 real-world calls, saving 311.85 hours of active engagement. Empirical evaluation with real-world data confirms its accuracy, while a case study and extensive user study highlight its effectiveness in enhancing call-taking performance.","doi":"10.24963/ijcai.2025/1065","url":"https://ijcai.org/proceedings/2025/1065","pdf":"https://ijcai.org/proceedings/2025/1065.pdf","markdown":"https://ijcai.org/proceedings/2025/1065.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1065","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI and Social Good","track":"AI and Social Good","number":1065,"pages":{"first":9582,"last":9590},"keywords":["Multidisciplinary Topics and Applications: General","Natural Language Processing: General"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}