collaborators

6 papers

cs.AI2026

Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning

Xuyang Zhao, Liting Zhang, Zichen Xu +4

On-policy self-distillation (OPSD) improves reasoning by using a privileged view of a model conditioned on reference solutions to supervise a student view that observes only the qu…

cs.CL2026

DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning

Yu Wang, Ming Fan, Xicheng Zhang +5

Chain-of-thought (CoT) supervision exposes intermediate rationales, but flat rationale targets usually optimize a single reasoning sequence and provide limited supervision on how l…

cs.CL2026

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

Shiwan Zhao, Zhihu Wang, Xuyang Zhao +10

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT…

cs.CL2026

Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration

Longxuan Wei, Yubo Zhang, Zijiao Zhang +7

Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). W…

cs.AI2025

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

Yu Wang, Shiwan Zhao, Zhihu Wang +6

The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks.…

cs.CL2025

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives

Zhihu Wang, Shiwan Zhao, Yu Wang +7

The Chain-of-Thought (CoT) paradigm has become a pivotal method for solving complex problems with large language models (LLMs). However, its application to domain-specific tasks re…