papers

Publications (8)

cs.CL2026

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…

#tool use#on-policy distillation#knowledge distillation#model calibration
cs.AI2026

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…

cs.AI2025

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…

cs.CL2026

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…

cs.IR2026

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…

cs.LG2023

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…