LLM Fine-Tuning

LLM: Large Language Model

LLM fine-tuning studies how additional training can adapt a pretrained model to new tasks, specialized knowledge, languages, or desired behaviors. Common approaches include supervised fine-tuning on curated or synthetic examples, preference optimization and reinforcement learning, and parameter-efficient methods such as LoRA and QLoRA that update only a small part of the model. Researchers also develop data-selection methods and selective layer or neuron updates to reduce training cost, and evaluate results on settings such as reasoning, code generation, multilingual tasks, and domain-specific question answering. A central challenge is gaining reliable task performance without losing general abilities or safety; results depend on the data, model, and evaluation, and retrieval can sometimes be a better alternative for adding knowledge.

Latest papers

758 papers76 papers in the last four weeks, up 15% on the four weeks before. 0.4% of all new papers.

Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation
Oct 27, 2026Yunqin Zhu, Yao XieLarge Language Model-Based Recommendation LLM Fine-Tuning
Georgia Institute of Technology, Atlanta, GA, USA
Think Twice: The Metis-1.6 Technical Report
Oct 27, 2026Giulianno VollmerLLM Training Efficient Language Model Training
Lernex Research
Hierarchical Low-Rank Reparameterization for Parameter-Efficient Fine-Tuning
Oct 27, 2026Rong Huang, Yi Xiong, Yuan-Yuan Cheng +1LLM Fine-Tuning Parameter-Efficient Fine-Tuning
University of Science and Technology of China, Hefei, Anhui 230026, China
Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation
Oct 26, 2026Zheng Lin, Zhanwei Wang, Yuxin Zhang +9LEO Satellite Networks LLM Inference
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, L-1855 Luxembourg, Luxembourg · Department of Computer and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong, China · Institute of Space Internet, Fudan University, Shanghai, China +5
Large Language Models: A Plain-Language Overview for Engineers
Oct 25, 2026Bahaeddin TürkoğluLLM Training LLM Prompting
Department of Artificial Intelligence and Data Engineering, Ankara University, Ankara, Türkiye
LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning
Oct 22, 2026Keqi Deng, Ruchao Fan, Jinyu LiSparse Fine-Tuning LLM Fine-Tuning
Microsoft, USA
Where Do LLMs Learn to Recommend AI?
Oct 21, 2026Benaya Trabelsi, Jonathan Shaki, Sarit KrausLarge Language Model-Based Recommendation LLM Prompting
Bar-Ilan University
MuPACE: Learning to Pace Muon for LoRA Fine-Tuning
Oct 20, 2026Jan Kobiolka, Christian Frey, Josif GrabockaLearning Rate Scheduling Adaptive Learning Rate
Department of Computer Science, University of Technology Nuremberg, Nuremberg, Germany
Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing
Oct 20, 2026Xi Yang, Guodong Liu, Cheng Peng +7Recurrent Language Models Clinical NLP
Advanced Intelligence and Research Eli Lilly and Company Indianapolis, IN, USA · Dept. of Health Outcomes and Biomedical Informatics University of Florida Gainesville, FL, USA · Higher Education and Research NVIDIA Santa Clara, CA, USA +2
Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Oct 19, 2026Min-Seong Kim, Jongbok Won, Jeesup Park +2Safety-Preserving Fine-Tuning of Language Models LLM Fine-Tuning
Yonsei University
VHDLBench: Benchmarking and Fine-Tuning Large Language Models for VHDL-Based Chip Design
Oct 19, 2026Patrik Drazic, Benaoumeur Senouci, Boualem BenatallahElectronic Design Automation Code Generation
University of Southern Denmark, Sønderborg, Denmark · RINN AI-Research Ireland Centre for AI and Data Science, Dublin City University Dublin, Ireland
NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
Oct 19, 2026Jianhao Zhang, Ou Wu, Yi DuLLM Fine-Tuning Data Selection for Language Model Fine-Tuning
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China · Computer Network Information Center, Chinese Academy of Sciences, Beijing, China
Safety Offset Learning: When Benign Fine-Tuning Misaligns LLMs
Oct 19, 2026Jesson Wang, Zhanhao Hu, Minghao Lin +3LLM Fine-Tuning LLM Safety Alignment
University of Southern California · University of California, Berkeley · University of Washington
First-Order LoRA Training with Phone NPUs
Oct 17, 2026Xu Zheng, Wei Cheng, Zhuomin Chen +4On-Device Training LLM Fine-Tuning
Florida International University, Miami, FL, USA · NEC Laboratories America, Princeton, NJ, USA · North Carolina State University, Raleigh, NC, USA +2
DKnown-Jev: Fine-Tuning and Evaluation of a JEV-Style Model for Tasks Involving Normative Knowledge
Oct 17, 2026Qi Li, Jianjun Xu, Pingtao WeiLLM Fine-Tuning LLM Evaluation
Beijing Caizhi Tech, Beijing, China
Beyond Clean Accuracy: The Practical Challenges and Benefits of Pixel-Based Language Models
Oct 16, 2026Haowen Tang, Wei Xia, Raoyuan Zhao +2Language Model Robustness LLM Fine-Tuning
Center for Information and Language Processing, LMU Munich · Munich Center for Machine Learning (MCML)
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
Oct 15, 2026Faridoun Mehri, Hinrich SchützeLanguage Model Generalization Factual Knowledge in Language Models
Center for Information and Language Processing, LMU Munich Munich Center for Machine Learning (MCML)
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
Oct 15, 2026Arnav Chavan, Kusha Sareen, Rishabh Tiwari +6Continual Learning for LLMs LLM Fine-Tuning
UC Berkeley · Mila · McGill University +5
Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization
Oct 15, 2026Egecan Çelik Evgin, İlknur Karadeniz, Olcay Taner YıldızText Summarization Summarization Evaluation
Department of Computer Science, Özyeğin University, İstanbul, Türkiye · Department of Computer Engineering, Galatasaray University, İstanbul, Türkiye · Department of Artificial Intelligence and Data Engineering, Özyeğin University, İstanbul, Türkiye
How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts
Oct 14, 2026Annabelle Sujun Tang, Wei Tang, Songyao Jiang +7Compiler Optimization Code Optimization
University of California, San Diego · Amazon Annapurna Labs
Wolof-Adapted Industry-Ready Open-Weight Language Models
Oct 14, 2026Gwénolé Lecorvé, Delphine Charlet, Pierre Adam +15Language Modeling Open-Weight Language Models
Orange Research, France
Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets
Oct 14, 2026Gwen Legate, Rahaf Aljundi, Eugene BelilovskyFederated Learning Heterogeneous Federated Learning
Concordia University · Mila · Toyota Motor Europe
Qwenfant: Train Big Character-level BabyLMs on Concise Parallel Text
Oct 13, 2026Lukas Edman, Alexander FraserLanguage Modeling Language Model Pretraining
School of Computation, Information and Technology, TU Munich · Munich Center for Machine Learning · Munich Data Science Institute
Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs
Oct 13, 2026Divyanshu Bathla, Parag Singla, Jitin SinglaBack-Translation Low-Resource MT
IIT Roorkee · IIT Delhi
Geometric Calibration of Supervised Fine-Tuning
Oct 13, 2026Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu +4LLM Fine-Tuning Supervised Fine-Tuning
Nanyang Technological University · University of California, Los Angeles
How Low Can You Go: Fine-Tuning LLMs with Bayesian Optimization (LlMBO)
Oct 13, 2026Aditya Kulkarni, Davide Sartor, Carlos Soto +1LLM Fine-Tuning Fine-Tuning Language Models
Department of Physics, University of Massachusetts Amherst · Department of Mathematics and Statistics, University of Massachusetts Amherst
Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages
Oct 13, 2026Ramchand Kumaresan, Madhusudhanan G, Kaushik KezendiraneLanguage Modeling Low-Resource Language Processing
Murai Labs · Independent researcher
Releasing the Inner Jev: A Simple Recipe for Open Decision Models
Oct 12, 2026Jonathan Geuter, Andrew Cheng, David Alvarez-MelisLLM Decision-Making LLM Fine-Tuning
Harvard University · Kempner Institute
StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning
Oct 12, 2026Xuanlin Yang, Jia Li, Zhouchen LinZeroth-Order Optimization Memory-Efficient Fine-Tuning
Peking University · Beijing Normal University
Zeroth-Order Fine-Tuning of LLMs in Learnable Low-Rank Subspaces
Oct 10, 2026Chuang Tong, Ling ChenLLM Fine-Tuning Zeroth-Order Optimization
State Key Laboratory of Blockchain and Data Security, Zhejiang University · College of Computer Science and Technology, Zhejiang University

Oct 27, 2026J/K move · Enter open · S save

Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation

Yunqin Zhu, Yao Xie

Georgia Institute of Technology, Atlanta, GA, USA

Large Language Model-Based Recommendation LLM Fine-Tuning Attention Mechanisms LLM Inference Acceleration LLM Context Compression

Open paper AskPDF arXiv

LLM-based generative recommendation reads long, text-rich interaction histories but generates only short semantic identifiers (SIDs). This asymmetry makes supervised fine-tuning inefficient: encoding the history is expensive, yet each history usually provides supervision for only one target. We present Merge and Branch (M&B) to reduce input cost and learn more from each encoded history. Merge compresses each historical item's SID and text into a small number of learned tokens. Branch uses the compressed history to predict multiple target SIDs. To share history computation while keeping these targets independent, M&B organizes each example as a shallow, wide tree. We develop tree FlashAttention to execute this layout efficiently, processing the shared history once and propagating gradients from every branch for end-to-end training. A tree-structured key/value cache extends history sharing to constrained decoding. Experiments on public benchmarks show that M&B outperforms strong recommendation baselines while substantially improving training and decoding efficiency.