作者位次 #2/4SIGIR 2026Poster· Information Retrieval (Resource)
Refairmulate: A Large-Scale Dataset for Gender-Fair Query Reformulations
Hai Son Le · Shirin Seyedsalehi · Morteza Zihayat · Ebrahim Bagheri
摘要
Information Retrieval systems can amplify societal inequalities when training data and ranking algorithms encode biases toward certain gender identities. Query reformulation methods are known to improve retrieval effectiveness, yet they seldom treat retrieval fairness as a first-class criterion....