# Sparse is Enough in Fine-tuning Pre-trained Large Language Models

arXiv: https://arxiv.org/abs/2312.11875 · HTML: https://mlsanity.com/paper/2312.11875/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 24 of 24)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)
- [Full Parameter Fine-tuning for Large Language Models with Limited Resources](https://mlsanity.com/paper/2306.09782/) (2023)
- [Visualizing and Understanding the Effectiveness of BERT](https://mlsanity.com/paper/1908.05620/) (2019)
- [A Strongly Quasiconvex PAC-Bayesian Bound](https://mlsanity.com/paper/1608.05610/) (2016)
- [Exploring loss function topology with cyclical learning rates](https://mlsanity.com/paper/1702.04283/) (2017)
- [Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training](https://mlsanity.com/paper/2004.04729/) (2020)

## Built on by (most cited first, 21 of 21)

- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [Parameter-Efficient Fine-Tuning of State Space Models](https://mlsanity.com/paper/2410.09016/) (2024)
- [PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs](https://mlsanity.com/paper/2508.17188/) (2025)
- [Sparse Matrix in Large Language Model Fine-tuning](https://mlsanity.com/paper/2405.15525/) (2024)
- [How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients](https://mlsanity.com/paper/2504.10766/) (2025)
- [Scalable UAV Multi-Hop Networking via Multi-Agent Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2505.08448/) (2025)
- [Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation](https://mlsanity.com/paper/2505.11235/) (2025)
- [Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution](https://mlsanity.com/paper/2505.24037/) (2025)
- [MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization](https://mlsanity.com/paper/2606.17526/) (2026)
- [GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters](https://mlsanity.com/paper/2510.19778/) (2025)
- [Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence](https://mlsanity.com/paper/2603.05960/) (2026)
- [5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2606.10488/) (2026)
- [Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning](https://mlsanity.com/paper/2607.09287/) (2026)
- [Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models](https://mlsanity.com/paper/2409.20181/) (2024)
- [GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation](https://mlsanity.com/paper/2508.16191/) (2025)
- [Random Initialization of Gated Sparse Adapters](https://mlsanity.com/paper/2511.01794/) (2025)
- [FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs](https://mlsanity.com/paper/2604.06297/) (2026)
- [One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning](https://mlsanity.com/paper/2605.06166/) (2026)

## Abstract (arXiv)

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscillations in the loss landscape and the quasi-sparsity in gradient distribution. Based on this, we propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://github.com/song-wx/SIFT/.