作者位次 #2/4SIGIR 2026Poster· Information Retrieval (Short)
REMICA: Reflective Memory and Interventional Context Alignment with Multi-Agent LLMs for Inappropriate Utterance Detection
Juyoung Kim · Ji-Hong Park · Sang-Min Choi · Gun-Woo Kim
摘要
Recently, multi-agent debate-based inference methods have been widely adopted for inappropriate utterance detection to aggregate diverse perspectives and improve explainability. However, performing real-time interactions for every input incurs substantial latency and cost, and may amplify error e...