作者位次 #6/6SIGIR 2026Oral· Information Retrieval (Perspective)
Evaluation Validity in Information Retrieval
Paul Thomas · Nick Craswell · Mark Sanderson · Seth Spielman · Robert Sim · Ryen W White
摘要
Information retrieval has long relied on evaluations that measure system performance. Improvements on standard evaluation protocols are interpreted as progress in system effectiveness, on the understanding that improved metrics indicate a better experience. However, most evaluations are a drastic...