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

Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
May 28, 2026Rahul Bissa, Abhishek Vyas, Yash JainVLM Evaluation Supervised Fine-Tuning
AprioriLabs
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models
May 28, 2026Qi Liu, Mingdi Sun, Yongyi He +5Supervised Fine-Tuning Fine-Tuning
University of Science and Technology of China · Huawei Cloud
Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
May 27, 2026Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima +2Supervised Fine-Tuning LLM Post-Training
The University of Tokyo
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
May 27, 2026Guijin Son, Seungyeop Yi, Minju Gwak +3Supervised Fine-Tuning LLM Mathematical Reasoning
Seoul National University · OneLineAI · Yonsei University
Fine-Tuning Dynamics of In-Context Factual Recall in Transformers
May 26, 2026Ruomin Huang, Eshaan Nichani, Jason D. Lee +1Supervised Fine-Tuning Transformer Attention
Duke University · Princeton University · UC Berkeley
Learning to Adapt SFT Data for Better Reasoning Generalization
May 26, 2026Lisong Sun, Li Wang, Chen Zhang +4Supervised Fine-Tuning LLM Post-Training
Beihang University · Tsinghua University · Nanyang Technological University +2
DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding
May 26, 2026Jianfei Zhao, Feng Zhang, Xin Sun +3Supervised Fine-Tuning Vision-Language Models
School of Computer Science and Technology, Beijing Institute of Technology · 2Zhongguancun Academy · 5Southeast Academy of Information Technology, Beijing Institute of Technology +2
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
May 25, 2026Yuelin Hu, Wei Liu, Zhenbo Yu +2Supervised Fine-Tuning Adaptive Loss Weighting
Shanghai Jiao Tong University · Shanghai Maritime University
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
May 21, 2026Jeanmely Rojas Nunez, Viraj Sawant, Nathan Allen +4Supervised Fine-Tuning Mechanistic Interpretability
Algoverse AI Research · Independent
Learnability-Informed Fine-Tuning of Diffusion Language Models
May 21, 2026Shubham Parashar, Atharv Chagi, Jacob Helwig +5Supervised Fine-Tuning Diffusion Language Models
Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA · Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
May 21, 2026Dong NieSupervised Fine-Tuning RL for Language Model Reasoning
Independent Researcher
From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
May 21, 2026Murong Ma, Tianyu Chen, Yun Lin +7Supervised Fine-Tuning Software Engineering Agents
1National University of Singapore · 2Microsoft Research Asia · 3Shanghai Jiao Tong University +1
ACC: Compiling Agent Trajectories for Long-Context Training
May 21, 2026Qisheng Su, Zhen Fang, Shiting Huang +8Supervised Fine-Tuning Long-Context Modeling
MoE Key Lab of BIPC, University of Science and Technology of China · Shanghai Innovation Institute · Shanghai AI Laboratory
PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning
May 20, 2026Qihao Lin, Guanxu Chen, Dongrui Liu +1Supervised Fine-Tuning LLM Fine-Tuning
Shanghai Artificial Intelligence Laboratory
Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
May 20, 2026Lukas Twist, Helen Yannakoudakis, Jie M. ZhangSupervised Fine-Tuning Reasoning Evaluation
King’s College London London, UK
When Reasoning Supervision Hurts: TTCW-Based Long-Form Literary Review Generation
May 19, 2026Jinlong Liu, Mohammed Bahja, Mark LeeSupervised Fine-Tuning Creativity Assessment
School of Computer Science, University of Birmingham, United Kingdom
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
May 18, 2026Junpeng Zhang, Lei Cheng, Guoxi Zhang +3Supervised Fine-Tuning LLM Fine-Tuning
Shanghai Jiao Tong University · Beijing Institute for General Artificial Intelligence · UniDT +1
InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
May 14, 2026Mahdi Sabbaghi, George Pappas, Adel Javanmard +1Supervised Fine-Tuning Adaptive Loss Weighting
University of Pennsylvania · University of Southern California
LIFT: Last-Mile Fine-Tuning for Table Explicitation
May 13, 2026Divij Khaitan, Ashish TiwariSupervised Fine-Tuning Fine-Tuning
Microsoft Corporation Bangalore, India · Microsoft Corporation Redmond, WA 98052 USA
From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning
May 13, 2026Haodong Wu, Jiahao Zhang, Lijie Hu +1Supervised Fine-Tuning Training Data Curation
The Hong Kong University of Science and Technology (Guangzhou) · Mohamed bin Zayed University of Artificial Intelligence
Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
May 13, 2026Siyuan Liu, Tinghong Chen, Xinghan Li +2Supervised Fine-Tuning Training Data Selection
IIIS, Tsinghua University · College of AI, Tsinghua University · Shanghai Qi Zhi Institute +1
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
May 12, 2026Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak +3Supervised Fine-Tuning LLM Alignment
Carnegie Mellon University
How Useful Is Cross-Domain Generalization for Training LLM Monitors?
May 12, 2026Sam Martin, Fabien RogerSupervised Fine-Tuning Cross-Domain Generalization
Anthropic Fellows Program · Anthropic
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
May 12, 2026Sae Furukawa, Alina OpreaSupervised Fine-Tuning Privacy Leakage in Language Models
Northeastern University Boston, Massachusetts, USA
Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 Models
May 12, 2026Igor StrozziSupervised Fine-Tuning LLM Evaluation
Applied Mathematics Department Federal University of Rio de Janeiro
Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
May 12, 2026Shuo Xu, Jiakun Zhang, Junyu Lai +2Supervised Fine-Tuning Automated Theorem Proving
State Key Laboratory for Novel Software Technology, Nanjing University, China
A Mechanistic Investigation of Supervised Fine Tuning
May 12, 2026Ruhaan ChopraSupervised Fine-Tuning LLM Alignment
Independent Researcher
Step Rejection Fine-Tuning: A Practical Distillation Recipe
May 11, 2026Igor Slinko, Ilia Zavidnyi, Egor Bogomolov +1Supervised Fine-Tuning LLM Agent Training
JetBrains Research
Annotations Mitigate Post-Training Mode Collapse
May 11, 2026Jacob Mitchell Springer, Madhu Advani, Lukas Aichberger +7Supervised Fine-Tuning Diverse Text Generation
Carnegie Mellon University · Apple · Johannes Kepler University Linz
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
May 11, 2026Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3Supervised Fine-Tuning Self-Attention
The Chinese University of Hong Kong · Huawei Technologies Co., Ltd

May 28, 2026J/K move · Enter open · S save

Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark

Rahul Bissa, Abhishek Vyas, Yash Jain

AprioriLabs

VLM Evaluation Supervised Fine-Tuning

Open paper AskPDF arXiv

We benchmark three supervised fine-tuned models against frontier zero-shot baselines on a 661-row held-out slice of PiSAR (Persona, intent, Screen, Action, Rationale), a 12,929-tuple corpus of screen-anchored behavioural rationales curated from public app-store reviews, Pew American Trends Panel demographics, and the OPeRA shopper traces. Every model, frontier or fine-tuned, is evaluated on the same 661-row slice with the same scoring pipeline. Two findings. First, frontier zero-shot baselines (Claude Opus 4.7 and GPT-5.5) reach sem_sim 0.459 and 0.482 respectively; a fine-tuned Qwen3-VL-8B-Instruct reaches 0.783 and clears sem_sim >= 0.7 on 79% of rows, against 1-2% for either frontier baseline, a gap of 0.30 absolute on the same test set. Second, the same training data and recipe on Gemma-4-26B-A4B-IT scores only 0.441, in the same band as the frontier zero-shot baselines rather than the fine-tuned Qwen. We read this as a recipe-vs-model mismatch: the reasoning-tuned high-parameter model resists displacement and would likely need either more data or a stronger fine-tuning method.