一作SIGIR 2026Oral· Information Retrieval (Full)
Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval
Wentai Xie · Parker Carlson · Shanxiu He · Tao Yang
摘要
Recent work on neural sparse retrieval has demonstrated strong relevance by leveraging Large Language Models (LLMs) for semantic term expansion. However, learned models paired with previous sparsification techniques still yield overly long document and query vectors partly due to a large LLM voca...