5 papers
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
Anhao Zhao, Junlong Tong, Yingqi Fan +3
Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo esti…
CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring
Xuan Lu, Haohang Huang, Yingqi Fan +5
Large language model (LLM) rerankers have become an important component of modern retrieval and retrieval-augmented generation pipelines, but their high computational cost limits t…
GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
Yuyang Bai, Zhuofeng Li, Ping Nie +2
Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than…
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Zhuofeng Li, Haoxiang Zhang, Cong Wei +16
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoni…
SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction
Hangxiao Zhu, Yuyu Zhang, Ping Nie +1
The rapid growth of scientific literature calls for automated methods to assess and predict research impact. Prior work has largely focused on citation-based metrics, leaving limit…