5 papers
Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval
Yunhan Li, Mingjie Xie, Zeyang Shi +2
Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, under a sufficiently large but pract…
LegalCiteTrust: Benchmarking Citation Trustworthiness in Chinese Long-Form Legal Research Reports
Yunhan Li, Mingjie Xie, Zeyang Shi +2
Long-form legal research reports increasingly rely on LLMs and agentic research systems, but their reliability depends not only on answering the task, but also on whether cited leg…
Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
Longkun Hao, Hongyu Lin, Hao Li +11
Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, determining the optimal timing for expert i…
Optimizing Retrieval Components for a Shared Backbone via Component-Wise Multi-Stage Training
Yunhan Li, Mingjie Xie, Zihan Gong +3
Recent advances in embedding-based retrieval have enabled dense retrievers to serve as core infrastructure in many industrial systems, where a single retrieval backbone is often sh…
LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval
Yunhan Li, Mingjie Xie, Gaoli Kang +3
Statute retrieval is essential for legal assistance and judicial decision support, yet real-world legal queries are often implicit, multi-issue, and expressed in colloquial or unde…