一作SIGIR 2026Poster· Information Retrieval (Short)
G-CoS: An Interpretable Gain-Cost Framework for User Satisfaction Estimation in Generative Information Retrieval
Jia-Ling Shi · Zhijing Wu · Yidong Liang · Xian-Ling Mao
摘要
User satisfaction serves as a key indicator of search experience in Generative Information Retrieval (GenIR) systems, and its accurate estimation is essential for system optimization. Extensive research in traditional IR has established interaction signals (e.g., dwell time, clicks, query reformu...