Copertina

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Zixian, Yang, Kaichen, Huang, Xu, Hao, Feiyang, Ge, Qiming, Li, Bowen, Du, He, Chen, Kai, Guo, Qipeng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
di: Gao, Changjiang, et al.
Pubblicazione: (2026)

RL Fine-Tuning Heals OOD Forgetting in SFT
di: Jin, Hangzhan, et al.
Pubblicazione: (2025)

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning
di: Du, He, et al.
Pubblicazione: (2025)

SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
di: Chen, Yijie, et al.
Pubblicazione: (2026)

Turning Students into Readers: Librarians and Teachers Cooperating.
di: Farber, Evan Ira
Pubblicazione: (1988)

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
di: Deb, Rohan, et al.
Pubblicazione: (2025)

SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
di: Lin, Jiacheng, et al.
Pubblicazione: (2025)

SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image Reconstruction
di: Gayathri, Matcha Naga, et al.
Pubblicazione: (2023)

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
di: Song, Feifan, et al.
Pubblicazione: (2024)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
di: Chen, Liang, et al.
Pubblicazione: (2025)

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
di: Du, He, et al.
Pubblicazione: (2026)

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
di: Hong, Joey, et al.
Pubblicazione: (2024)

SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Models
di: Kim, Gyuhak, et al.
Pubblicazione: (2025)

FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
di: Pei, Zehua, et al.
Pubblicazione: (2026)

Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data
di: Zhuang, Xinlin, et al.
Pubblicazione: (2025)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
di: Kang, Feiyang, et al.
Pubblicazione: (2025)

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
di: Zhu, Taojie, et al.
Pubblicazione: (2026)

Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
di: Huang, Feiyang, et al.
Pubblicazione: (2026)

Learning to Adapt SFT Data for Better Reasoning Generalization
di: Sun, Lisong, et al.
Pubblicazione: (2026)

DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
di: Hu, Hanxu, et al.
Pubblicazione: (2026)

ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning
di: Van Vo, Tuan, et al.
Pubblicazione: (2025)

Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
di: Ge, Qiming, et al.
Pubblicazione: (2025)

Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience
di: Diaz, Manfred, et al.
Pubblicazione: (2024)

Teacher Judgments of Student Reading Interests: How Accurate Are They?
di: Stoefen-Fisher, Jill M.
Pubblicazione: (1990)

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
di: Li, Ming, et al.
Pubblicazione: (2024)

Students as Teachers
di: Fee, Heidi
Pubblicazione: (2022)

Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games
di: Yang, Yunhao, et al.
Pubblicazione: (2024)

Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
di: Kang, Feiyang, et al.
Pubblicazione: (2024)

Real-Time Hardware-Free HIFU Interference Suppression via Teacher-Student Diffusion Framework
di: Cai, Dejia, et al.
Pubblicazione: (2025)

TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning
di: Huang, Xu, et al.
Pubblicazione: (2026)

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
di: Wang, Bo, et al.
Pubblicazione: (2025)

PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data
di: Xiong, Kai, et al.
Pubblicazione: (2025)

Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation
di: Shen, Chaomin, et al.
Pubblicazione: (2024)

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
di: Miao, Ziyang, et al.
Pubblicazione: (2025)

OPCap:Object-aware Prompting Captioning
di: Huang, Feiyang
Pubblicazione: (2024)

ViTOC: Vision Transformer and Object-aware Captioner
di: Huang, Feiyang
Pubblicazione: (2024)

SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
di: Yi, Seungjun, et al.
Pubblicazione: (2025)

GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models
di: Yi, Qiang, et al.
Pubblicazione: (2025)

Hint Tuning: Less Data Makes Better Reasoners
di: Fan, Siqi, et al.
Pubblicazione: (2026)

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
di: Zhang, Xuechen, et al.
Pubblicazione: (2025)