Supervised Fine-Tuning

Also known as SFT

Follow this topic Ask about this topic

Latest papers 211

29 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

All topics

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Jun 26, 2026Changyue Li, Jiaming He, Youliang Yuan +4Supervised Fine-Tuning LLM Safety Alignment
The Chinese University of Hong Kong, Shenzhen · Ant Group · Lero the Research Ireland Centre for Software, University of Limerick
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
Jun 25, 2026Qiaobo Hao, Yangqian Wu, Shunyi Wang +5Supervised Fine-Tuning RL for Language Models
ZTE NebulaL0 Post-Training Team
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Jun 24, 2026Yupu Hao, Zhuoran Jin, Huanxuan Liao +2Supervised Fine-Tuning LLM Reliability
1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artiﬁcial Intelligence, University of Chinese Academy of Sciences, Beijing, China
Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection
Jun 24, 2026Zihan Pan, Sailor Hardik, Jinyang WuSupervised Fine-Tuning Audio Deepfake Detection
Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, 138632, Singapore
Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act
Jun 18, 2026Ali Asaria, Tony Salomone, Deep GandhiSupervised Fine-Tuning Retrieval-Augmented Generation
Transformer Lab
SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR
Jun 16, 2026Siddharth Aphale, Kelly LiuSupervised Fine-Tuning Group Relative Policy Optimization
Stanford University, Stanford, CA, USA.
Perceptual compensation for tonal context in self-supervised speech models
Jun 16, 2026James Kirby, Ioana Krehan, Michele GubianSupervised Fine-Tuning Speech Prosody
Institute for Phonetics and Speech Processing, LMU Munich, Germany
DRIFT: Refining Instruction Data via On-Policy Data Attribution
Jun 16, 2026Zefan Wang, Lincheng Li, Tianyu Yu +1Supervised Fine-Tuning Training Data Curation
Tsinghua University
ProCUA-SFT Technical Report
Jun 15, 2026Jaehun Jung, Ximing Lu, Brandon Cui +11Supervised Fine-Tuning Computer-Use Agents
1NVIDIA · University of Washington
How Post-Training Shapes Biological Reasoning Models
Jun 15, 2026Lukas Fesser, Hanlin Zhang, Michelle M. Li +5Neural Network Generalization Supervised Fine-Tuning
Harvard University · Google DeepMind · Google Research
Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding
Jun 11, 2026Ziqing Wang, Weihao Li, Shijie Chen +2Supervised Fine-Tuning Automated Medical Coding
Northwestern University
CODEBLOCK: Learning to Supervise Code at the Right Granularity
Jun 10, 2026Zhijie Deng, Ling Li, Jinlong Pang +5Supervised Fine-Tuning Code Language Models
Hong Kong University of Science and Technology (Guangzhou) · UC Santa Cruz · Ant Group +1
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
Jun 9, 2026Tong Xie, Yuanhao Ban, Yunqi Hong +3Supervised Fine-Tuning Fine-Tuning
University of California, Los Angeles (UCLA) · Arena
Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
Jun 9, 2026Xinyu Zhou, Boyu Zhu, Yi Xu +4Long-Context Retrieval Supervised Fine-Tuning
1LARK, HKUST(GZ) · 2UCL · 3Mistral AI +3
Don't waste SAM
Jun 9, 2026Nermeen Abou Baker, Uwe HandmannSupervised Fine-Tuning Promptable Image Segmentation
1- Ruhr West University of Applied Sciences - Dept of Computer Science Lutzowstrassse 5, 46236 Bottrop - Germany
Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction
Jun 9, 2026Buxin Su, Bingxuan Li, Cheng Qian +3Supervised Fine-Tuning Clinical Outcome Prediction
University of Pennsylvania · University of Illinois Urbana-Champaign · University of California, Merced
PriFT: Prior-Support Guided Supervised Fine-Tuning
Jun 8, 2026Ke Wang, Shuangqi Li, Mathieu Salzmann +1Supervised Fine-Tuning Fine-Tuning
EPFL, Lausanne, Switzerland
Stage-1 Controls the Entropy Regime, Not the Outcome
Jun 8, 2026Jianxiong ShenSupervised Fine-Tuning VLM Reasoning
When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff
Jun 7, 2026Runze Liu, Jiashun Liu, Xu Wan +2Supervised Fine-Tuning RL Post-Training
Hong Kong University of Science and Technology · Zhejiang University · State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
Jun 5, 2026Yongliang Miao, Fengyuan Liu, Wei Shi +4Supervised Fine-Tuning LLM Mathematical Reasoning
The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory · New Jersey Institute of Technology +1
TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
Jun 5, 2026Chengkai Zhang, Ziteng Liu, Junpu Wang +4Supervised Fine-Tuning Adapter Tuning
Meta AI
Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning
Jun 3, 2026Chongyang He, Rui Zhang, Zixuan Wang +1Supervised Fine-Tuning RL for Language Model Reasoning
1Tsinghua University · 2National University of Singapore · 3DiDi +1
(Mis)generalization of Helpful-only Fine-tuning
Jun 3, 2026Mohammad Omar Khursheed, Baram Sosis, Fabien RogerSupervised Fine-Tuning LLM Sycophancy
Anthropic Fellows Program MATS · Anthropic
RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training
Jun 2, 2026Rachit Bansal, Clara Mohri, Tian Qin +2Language Model Pretraining Supervised Fine-Tuning
Harvard University
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Jun 2, 2026Patrick Emami, Nan Qiang, Peter GrafSupervised Fine-Tuning LLM Planning
National Laboratory of the Rockies · Epic Systems
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Jun 1, 2026Ivan Sabolić, Marin Oršić, Josip Šarić +1Supervised Fine-Tuning VLM Robustness
Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia.
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
May 31, 2026Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe +1Supervised Fine-Tuning Emergent Misalignment in Language Models
University of Maryland
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
May 29, 2026Jian Mu, Tianyi Lin, Chengwei Qin +2Supervised Fine-Tuning RL for Language Models
The Hong Kong University of Science and Technology (Guangzhou) · The Chinese University of Hong Kong, Shenzhen.
RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
May 29, 2026Yuduo Li, Xiaofeng Shi, Qian Kou +2Supervised Fine-Tuning Fine-Tuning
Beijing Academy of Artificial Intelligence (BAAI) · Beijing Jiaotong University (BJTU)
On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
May 28, 2026Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1Supervised Fine-Tuning Vision-Language Models
University of California, Los Angeles

Jun 26, 2026J/K move · Enter open · S save

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

Changyue Li, Jiaming He, Youliang Yuan, Jialin Wu+3

The Chinese University of Hong Kong, Shenzhen · Ant Group · Lero the Research Ireland Centre for Software, University of Limerick

Supervised Fine-Tuning LLM Safety Alignment LLM Safety LLM Post-Training

Open paper AskPDF arXiv

Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety alignment. To recover safety without re-running full alignment, existing realignment methods focus on calibrating the integration of safety patches into fine-tuned models. These methods exhibit a persistent safety-utility trade-off: weak repair leaves harmful behavior intact, while stronger repair increasingly damages the benign task. This paper shifts the focus from online calibration to offline patch learning and aims to learn a safety patch that restores safety while preserving task-specific capabilities. To this end, we propose TRACE, which simulates harmful SFT trajectories to produce progressively corrupted model states, and optimizes a safety patch simultaneously across these states. TRACE trains the safety patch during the offline stage, and reuses it across all user checkpoints without per-user calibration. We evaluate two representative models using three harmful SFT datasets, together with three utility benchmarks. Across six benchmarks and two models, TRACE consistently dominates the safety-utility frontier. TRACE improves the safety rate by up to 77 percentage points over the best baselines, while maintaining comparable utility to the undefended fine-tuned model.