← Search

Wenhan Liu

2 accepted papers

2025

CoRanking: Collaborative Ranking with Small and Large Ranking Agents

EMNLP 2025

Listwise ranking based on Large Language Models (LLMs) has achieved state-of-the-art performance in Information Retrieval (IR).However, their effectiveness often depends on LLMs with massive parameter scales and computationally expensive sliding window processing, leading to substantial efficiency b

2025

Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models

ACL 2025long

Large Language Models (LLMs) have shown exciting performance in listwise passage ranking. Due to the limited input length, existing methods often adopt the sliding window strategy. Such a strategy, though effective, is inefficient as it involves repetitive and serialized processing, which usually re…