Selective Fine-Tuning

Follow this topic Ask about this topic

Selective fine-tuning studies how to adapt pretrained models efficiently while preserving useful capabilities and reducing compute, memory, or privacy costs. Approaches rank layers and parameters using gradients, Fisher information, activations, routing, or sensitivity, and select training data or tokens using utility, influence, or alignment signals. These methods are used for language-model adaptation, safety and unlearning, continual learning, vision, and other domains, with comparisons often measuring task accuracy alongside retention, forgetting, and resource use. A central tension is that importance does not always mean a component can be trained effectively in isolation, and choices that help a current task may harm general capabilities or future learning.

Latest papers

43 papers2 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation
Oct 26, 2026Haocheng Mei, Yuchuan Tian, Ye Yuan +5LLM Reranking Learning to Rank
Peking University · SUIBE · University of Macau +2
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Oct 14, 2026Yuxuan Wang, Guangxiang Zhao, Xinyu Tan +6Supervised Fine-Tuning Selective Fine-Tuning
Peking University · Xidian University · Qiyuan Tech +1
Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention
Oct 8, 2026Zhiqiang Pang, Zihong Sun, Qi Xie +3LLM Fine-Tuning Selective Fine-Tuning
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, China
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Sep 27, 2026Cunchun Li, Haonan He, Yifan Gao +4Supervised Fine-Tuning Adaptive Loss Weighting
Shanghai AI Laboratory · University of Science and Technology of China · Fudan University +2
What Should We Freeze? Guarded Freezing: Connectivity Shapes the Fine-Tuning of Pretrained Models
Sep 26, 2026Leonel AguilarFine-Tuning Selective Fine-Tuning
Chair of Cognitive Science, ETH Zürich
From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs
Sep 22, 2026Zhentao Tan, Chang Liu, Yao Liu +2Mixture-of-Experts Language Models Sparse Fine-Tuning
Alibaba Group · Southeast University
What Does Layer-Importance Reveal About Transformers and State-Space Models?
Sep 15, 2026Istabrak Abbes, Nizar Islah, Irina Rish +1Transformer Interpretability Selective SSMs
Chandar Research Lab · Mila - Quebec AI Institute · Université de Montréal +2
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Sep 12, 2026Fei Yuan, Changjiang Gao, Yilei Tu +3Fine-Tuning LLM Fine-Tuning
Shanghai Artificial Intelligence Laboratory · National Key Laboratory for Novel Software Technology, Nanjing University
Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models
Sep 5, 2026Zeyu Wu, Junchao Wu, Shudong Liu +8LLM Fine-Tuning Supervised Fine-Tuning
NLP2CT Lab, Faculty of Information Science and Computing, University of Macau · Alibaba Group · Nanjing University +3
MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing
Jul 27, 2026Xiao Han, Pinbo Wang, Yuanshao Zhu +2Graph Neural Networks Concept Drift
\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating
Jul 24, 2026Jianghui Wang, Silong Yong, Francesco Orabona +3Fine-Tuning Memory-Efficient Fine-Tuning
King Abdullah University of Science and Technology · Carnegie Mellon University
Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning
Jul 23, 2026Yi Xiong, Yuan-Yuan Cheng, Xiao-Ming FuFine-Tuning Diffusion Model Fine-Tuning
University of Science and Technology of China, China
PPL-Factory: Task-Aware and Budget-Aware Data Selection from Language Modeling to Reasoning
Jul 20, 2026Hang Zhang, Warren J. GrossLLM Fine-Tuning Efficient Language Model Training
Department of Electrical and Computer Engineering, McGill University Montreal, QC, Canada
TopoTuner: Topological Finetuning of Large Language Models
Jul 18, 2026Abdulkadir Erol, Yash Mahajan, Vepaul Hariprashad +4Fine-Tuning LLM Fine-Tuning
Department of Computer Science University of Central Florida Orlando, USA · Department of Computer Science University of Manitoba Canada · Department of Finance University of Central Florida Orlando, USA
Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning
Jul 10, 2026Ivan Ilin, Philip Zmushko, Peter RichtárikMemory-Efficient Fine-Tuning Low-Rank Adaptation
KAUST
Super Weights in LLMs and the Failure of Selective Training
Jul 9, 2026Shreyas Subramanian, Adewale Akinfaderin, Akarsha SehwagLLM Pruning Fine-Tuning
Amazon Web Services
Online Data Selection Is Implicit Alignment
Jul 8, 2026Aoxiong Zeng, Yuxin Yang, Xiangquan YangSupervised Fine-Tuning LLM Alignment
East China Normal University · Shanghai University
Pretraining Curricula Enable Selective Fine-tuning
Jul 6, 2026Sebastian A. Bruijns, Jirko Rubruck, Mia H. Whitefield +3Disentangled Representation Learning Fine-Tuning
University of Oxford · University of Oxford & Martian · Martian
Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
Jun 8, 2026Ghodsiyeh Rostami, Po-Han Chen, Mahdi S. HosseiniFine-Tuning Vision Foundation Model Adaptation
Concordia University · Concordia University Mila - Québec AI Institute
HARP: Efficient Data Selection for Finetuning Large Language Models
Jun 5, 2026Ning Wang, Zhengxin Zhang, Maosen Tang +3LLM Fine-Tuning Active Learning
Cornell University · The Hong Kong University of Science and Technology
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
May 29, 2026Xiaosong Han, Ke Chen, Xindi Dai +7Continual Learning for LLMs LLM Fine-Tuning
Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education · College of Computer Science and Technology, Jilin University Changchun, China · College of Software, Jilin University Changchun, China +3
The Long-Term Effects of Data Selection in LLM Fine-Tuning
May 28, 2026Yuxin Yang, Aoxiong Zeng, Xiangquan YangContinual Learning for LLMs LLM Fine-Tuning
Shanghai University · East China Normal University
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
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
May 24, 2026Xiangtian Ji, Yuxin Chen, Zhengzhou Cai +3Fine-Tuning LLM Interpretability
National University of Singapore · Beijing University of Posts and Telecommunications · University of Science and Technology of China
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
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
May 17, 2026Haichao Sha, Zihao Wang, Yuncheng Wu +2Fine-Tuning Privacy-Preserving Language Models
Renmin University of China · Nanyang Technological University
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
Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
May 12, 2026Yu-Hang Wu, Qin-Yuan Liu, Qiu-Yang Zhao +3Fine-Tuning Continued Pretraining
Nanhu Research Institute of China Electronic Science and Technology · School of Electronic and Electrical Engineering, Shanghai University of Engineering Science
One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
May 7, 2026Xinrui Chen, Liu Yang, Ou WuSupervised Fine-Tuning LLM Fine-Tuning
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences · College of Intelligence and Computing, Tianjin University
CRAFT: Clustered Regression for Adaptive Filtering of Training data
Apr 24, 2026Parthasarathi Panda, Asheswari Swain, Subhrakanta PandaData Selection Training Data Selection
1Google, USA · 2,3Department of Computer Science & Information Systems, BITS Pilani, Hyderabad, India

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

Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation

Haocheng Mei, Yuchuan Tian, Ye Yuan, Enhua Wu+4

Peking University · SUIBE · University of Macau+2

LLM Reranking Learning to Rank Selective Fine-Tuning Low-Rank Adaptation

Open paper AskPDF arXiv

JEV decision models pair a language model backbone with a lightweight scoring head to select among natural-language options. Direct selection compares candidate answers within one request, whereas entailment reranking evaluates each candidate in a separate natural language inference (NLI) request over fixed relation options. We examine whether the readout and adaptation choices used for direct selection remain effective for cross-request reranking. We combine a mean-span readout with selective backbone adaptation. Mean-span pooling replaces the option-ending pointer with an average of the contextualized states inside each NLI option, without adding head parameters. Selective adaptation retains low-rank updates in attention and gated DeltaNet projections while removing feed-forward adapters. On MC11, which averages accuracy over eleven reranking configurations from seven sources, selective adaptation improves NeoHorse-1-4B accuracy over the all-module baseline while cutting trainable parameters by more than half, and mean-span pooling yields further consistent gains at the same parameter count.