Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
Xuyang Zhao, Liting Zhang, Zichen Xu, Zhihu Wang, Xu Caiyue, Shiwan Zhao, Qicheng Li
Abstract
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 question. However, the teacher-provided token-level targets may depend on reference-specific information unavailable at inference time. We propose Problem-Space-Guided OPSD (PS-OPSD), which replaces the complete solution with trajectory-grounded guidance describing the initial state, goal conditions, constraints, and a selected state-transition path. The student rollout and OPSD objective remain unchanged. Across three mathematical reasoning benchmarks and model scales ranging from 1.7B to 8B, PS-OPSD achieves the highest aggregate question-only accuracy among the compared methods. Controlled experiments further indicate that guidance relevance and path coherence contribute to these gains, highlighting the representation of privileged information as an important design choice in OPSD.
Create a lesson
Related papers
MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education
Luyao Zhu, Xun Wei Yee, Wei Li et al.
Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
Jinli Hu, Ross M. Clarke, Yichuan Zhang et al.
Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows
Ashwini Kurady, Sri Sai Charith Grandhi, Rajesh Gupta et al.
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
Jiaxuan Jiang, Liyuan He, Zhixuan Fang
Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale
Liuyin Wang, Shuaipeng Jin, Jiwei Shi et al.
Clueing up LLMs with Tool-Augmented Deductive Reasoning
Rebecca Ansell, Autumn Toney-Wails