English
Related papers

Related papers: A Stability Analysis of Fine-Tuning a Pre-Trained …

200 papers

We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning. While prompting is often favored for its parameter efficiency and flexibility, it…

Artificial Intelligence · Computer Science 2025-06-26 Rahul Raja , Arpita Vats

Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch,…

Machine Learning · Computer Science 2026-02-02 Youngjoong Kim , Duhoe Kim , Woosung Kim , Jaesik Park

Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have shown empirical effectiveness on feature selection, ranking…

Machine Learning · Computer Science 2023-02-21 Jiahuan Wang , Jun Chen , Hong Chen , Bin Gu , Weifu Li , Xin Tang

The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in…

Machine Learning · Computer Science 2023-06-09 Simone Marullo , Matteo Tiezzi , Marco Gori , Stefano Melacci , Tinne Tuytelaars

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that…

Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with…

Machine Learning · Computer Science 2024-12-05 Fu-Yun Wang , Zhengyang Geng , Hongsheng Li

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Computation and Language · Computer Science 2025-09-04 Yarden Tzach , Ronit D. Gross , Ella Koresh , Shalom Rosner , Or Shpringer , Tal Halevi , Ido Kanter

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we…

Computation and Language · Computer Science 2021-06-16 Bo Zheng , Li Dong , Shaohan Huang , Wenhui Wang , Zewen Chi , Saksham Singhal , Wanxiang Che , Ting Liu , Xia Song , Furu Wei

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when…

Machine Learning · Computer Science 2022-11-01 Jiancong Xiao , Yanbo Fan , Ruoyu Sun , Jue Wang , Zhi-Quan Luo

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Clinical prediction models are increasingly used to support patient care, yet many deep learning-based approaches remain unstable, as their predictions can vary substantially when trained on different samples from the same population. Such…

Machine Learning · Computer Science 2026-02-13 Sara Matijevic , Christopher Yau

In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such…

Neural and Evolutionary Computing · Computer Science 2015-08-26 Rossella Cancelliere , Mario Gai , Patrick Gallinari , Luca Rubini

Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve…

Machine Learning · Computer Science 2026-01-15 Aditya Tanna , Pratinav Seth , Mohamed Bouadi , Vinay Kumar Sankarapu

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Computation and Language · Computer Science 2024-10-11 Minchan Kwon , Gaeun Kim , Jongsuk Kim , Haeil Lee , Junmo Kim

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important…

Computation and Language · Computer Science 2024-02-09 Angelica Chen , Jason Phang , Alicia Parrish , Vishakh Padmakumar , Chen Zhao , Samuel R. Bowman , Kyunghyun Cho

Fine-tuning is now the primary method for adapting large neural networks, but it also introduces new integrity risks. An untrusted party can insert backdoors, change safety behavior, or overwrite large parts of a model while claiming only…

Cryptography and Security · Computer Science 2026-04-07 Zhenhang Shang , Kani Chen

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Computation and Language · Computer Science 2023-06-12 Himanshu Gupta , Saurabh Arjun Sawant , Swaroop Mishra , Mutsumi Nakamura , Arindam Mitra , Santosh Mashetty , Chitta Baral