作者位次 #2/4SIGIR 2026Poster· Information Retrieval (Short)
Humans, LLMs, and Measures Do Not Align in Attributed Information Retrieval
Lukas Gienapp · Jenny Lang · Martin Potthast · Harrisen Scells
摘要
Evaluating attributed information retrieval (AIR) systems requires assessing both informativeness and attributability. To enable scalable evaluation, LLM-sourced ground truth data is frequently used, yet the validity of this practice remains unclear. We replicate the evaluation framework of Djedd...