一作SIGIR 2026Oral· Information Retrieval (Reproducibility)
Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance
Gregory Polyakov · Harrisen Scells · Carsten Eickhoff
摘要
Learned sparse retrieval models such as SPLADE combine the effectiveness of neural architectures with the efficiency of inverted indices. As these models assign weights to terms from a fixed vocabulary, interpretability is often touted as a major benefit of these models. However, the emergence of...