7 papers
Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking
Xiaoyang Chen, Jie Liu, Haijin Liang +5
In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to inferior classification, score p…
Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking
Yongqi Fan, Yuxiang Chu, Zhentao Xia +9
In the RAG paradigm, document ranking determines the evidence available to downstream generators. Through controlled analysis, we identify two phenomena underexplored by existing r…
TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking
Yongqi Fan, Xiaoyang Chen, Dezhi Ye +6
Reasoning-intensive ranking models built on Large Language Models (LLMs) have made notable progress. However, existing approaches often rely on large-scale LLMs and explicit Chain-…
Best Practices for Distilling Large Language Models into BERT for Web Search Ranking
Dezhi Ye, Junwei Hu, Jiabin Fan +4
Recent studies have highlighted the significant potential of Large Language Models (LLMs) as zero-shot relevance rankers. These methods predominantly utilize prompt learning to ass…
WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations
Haolin Deng, Chang Wang, Xin Li +6
Enhancing the attribution in large language models (LLMs) is a crucial task. One feasible approach is to enable LLMs to cite external sources that support their generations. Howeve…
Event-driven Real-time Retrieval in Web Search
Nan Yang, Shusen Zhang, Yannan Zhang +4
Information retrieval in real-time search presents unique challenges distinct from those encountered in classical web search. These challenges are particularly pronounced due to th…
Event-Centric Query Expansion in Web Search
Yanan Zhang, Weijie Cui, Yangfan Zhang +5
In search engines, query expansion (QE) is a crucial technique to improve search experience. Previous studies often rely on long-term search log mining, which leads to slow updates…