paper-with-me

Papers

LoRi: Low-Rank Distillation for Implicit Reasoning

2026-06-03 · Ryan Solgi, Jiayi Tian, Zheng Zhang arxiv

Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empirically find that hidden-state reasoning trajectories exhibit low-rank structure. Motivated by this observation, we propose a low-rank distillation framework that transfers reasoning by aligning teacher and student trajectories in a shared low-rank tensor subspace using first- and second-order statistics. The resulting formulation captures the global structure of reasoning while supporting a compact latent reasoning process. We evaluate the method across multiple model families, including LLaMA and Qwen, at different scales on mathematical reasoning benchmarks. Our approach consistently improves performance, especially on challenging multi-step tasks, approaching explicit CoT accuracy and outperforming prior iCoT distillation methods.

📄 PDF Abstract BibTeX arXiv:2606.05315

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress

2026-08-19 · Chen Yang, Haiyuan Wan, Rengrong Xiong, Yize Chen 외 arxiv

On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly as…

Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning

2026-09-14 · Xun Xu, Zaixi Zhang arxiv

Multi-teacher on-policy distillation (OPD) is becoming the standard way to integrate specialist capabilities into one model: train experts with RL, then distill them into the student on its own rollouts. Existing recipes…

Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility

2026-05-28 · Jiahao Huang, Fei Cheng, Junfeng Jiang, Akiko Aizawa arxiv

Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces th…

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization

2026-05-28 · Junlin He, Yihong Tang, Tong Nie, Guilong Li 외 arxiv

Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high training efficiency. Although these EDistilled LLMs achieve state-of-the…

Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning

2025-05-22 · Shicheng Xu, Liang Pang, Yunchang Zhu, Jia Gu 외

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths gen…

Reinforcement Learning (RL)