paper-with-me

Papers

Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation

2026-02-21 · Wei Guo, Siyuan Lu, Xiangdong Ran, Yiqi Tong, Yikun Ban, Zelong Xu, Jing Fan, Zixuan Huang, Xiao Zhang, Zhaojun Hu, Fuzhen Zhuang arxiv

Data allocation plays a critical role in federated large language model (LLM) and small language models (SLMs) reasoning collaboration. Nevertheless, existing data allocation methods fail to address an under-explored challenge in collaboration: bidirectional model learnability gap, where client-side SLMs cannot identify high-reward samples matching their learnability constraints for effective knowledge transfer from LLMs, while LLMs struggle to select samples contributing novel knowledge beyond their existing data. Furthermore, these collaboration frameworks face another key challenge: domain-agnostic reasoning transfer, where existing reasoning transfer methods fail to flexibly adapt to the local domain data, preventing SLMs from effectively acquiring step-by-step reasoning abilities within from general LLM. To address these challenges, we propose LaDa, a federated reasoning distillation framework with model learnability-aware data allocation. It introduces a model learnability-aware data filter that adaptively allocates high-reward samples based on the learnability gap between each SLM and LLM pair, effectively facilitating bidirectional knowledge transfer. We further design a domain adaptive reasoning distillation method that aligns joint probabilities of reasoning paths on filtered high-reward samples through contrastive distillation learning between SLM and LLM, enabling SLM to capture underlying reasoning patterns under local data distribution. LaDa operates as a plug-in module for existing collaboration frameworks, adapting knowledge transfer based on model learnability gaps.

📄 PDF Abstract BibTeX arXiv:2602.18749

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Models

2026-01-22 · Hanwen Zhang, Qiaojin Shen, Yuxi Liu, Yuesheng Zhu 외 arxiv

Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, …

Medical Image SegmentationKnowledge DistillationGeneral Knowledge

LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation

2026-05-28 · Tianrun Yu, Kaixiang Zhao, Chih-Chun Chen, Amanda Hughes 외 arxiv

We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a student model. Existing methods rely on heuristics such as trajectory qua…

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning

2026-05-26 · Zehao Liu, Yuanpu Cao, Jinghui Chen, Vasant G. Honavar arxiv

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-tea…

Reinforcement Learning

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants

2025-07-02 · Dongyi Ding, Tiannan Wang, Chenghao Zhu, Meiling Tao 외 arxiv

Large language models (LLMs) excel at reasoning tasks requiring long thought sequences for planning, reflection, and refinement. However, their substantial model size and high computational demands are impractical for wi…

Small Models Struggle to Learn from Strong Reasoners

2025-02-17 · Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang 외

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Mod…