Publications (8)
When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation
Jiabin Shen, Guang Chen, Chengjun Mao
The paper studies how multi-teacher on-policy distillation can cause language models to over-call tools, and introduces Soft Clamp, a token-level divergence calibration method that…
Answer Presence Drives RAG Rewriting Gains
Yuejie Li, Yueying Hua, Ke Yang +7
Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{rewriter} before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this g…
Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
Yekun Zhu, Guang Chen, Chengjun Mao
Large Language Models (LLMs) with chains-of-thought have demonstrated strong performance on an increasing range of tasks, particularly those involving complex logical reasoning. Ho…
Attention-guided Evidence Grounding for Spoken Question Answering
Ke Yang, Bolin Chen, Yuejie Li +5
Spoken Question Answering (Spoken QA) presents a challenging cross-modal problem: effectively aligning acoustic queries with textual knowledge while avoiding the latency and error…
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration
Yuejie Li, Ke Yang, Tao Wang +3
Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing method…
MOEF: Modeling Occasion Evolution in Frequency Domain for Promotion-Aware Click-Through Rate Prediction
Xiaofeng Pan, Yibin Shen, Jing Zhang +5
Promotions are becoming more important and prevalent in e-commerce to attract customers and boost sales, leading to frequent changes of occasions, which drives users to behave diff…