English
Related papers

Related papers: A Closer Look at Model Adaptation using Feature Di…

200 papers

Simplicity bias, the propensity of deep models to over-rely on simple features, has been identified as a potential reason for limited out-of-distribution generalization of neural networks (Shah et al., 2020). Despite the important…

Machine Learning · Statistics 2024-11-08 Nikita Tsoy , Nikola Konstantinov

Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks. In this work, we investigate SB in…

Computer Vision and Pattern Recognition · Computer Science 2023-02-08 Xiu-Shen Wei , Xuhao Sun , Yang Shen , Anqi Xu , Peng Wang , Faen Zhang

LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…

Machine Learning · Computer Science 2024-10-21 Yang Zhao , Li Du , Xiao Ding , Kai Xiong , Ting Liu , Bing Qin

With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications,…

Machine Learning · Computer Science 2024-05-28 Lu Tan , Huei Zhou , Yinxiang Huang , Zeming Zheng , Yujiu Yang

Given a family of linear constraints and a linear objective function one can consider whether to apply a Linear Programming (LP) algorithm or use a Linear Superiorization (LinSup) algorithm on this data. In the LP methodology one aims at…

Optimization and Control · Mathematics 2026-01-27 Jan Schröder , Yair Censor , Philipp Süss , Karl-Heinz Küfer

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages…

Computation and Language · Computer Science 2026-05-27 Lisong Sun , Li Wang , Chen Zhang , Jinyang Wu , Kui Zhang , Tianhao Peng , Wenjun Wu

Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train…

Machine Learning · Computer Science 2026-04-09 Zhiyuan Huang , Jiahao Chen , Bing Su

This research investigates the effectiveness of alignment techniques, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and a combined SFT+DPO approach on improving the safety and helpfulness of the OPT-350M language…

Computation and Language · Computer Science 2025-09-12 Piyush Pant

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Machine Learning · Computer Science 2023-10-03 Zhilin Zhao , Longbing Cao , Kun-Yu Lin

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Haoyu He , Jianfei Cai , Jing Zhang , Dacheng Tao , Bohan Zhuang

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust…

Machine Learning · Computer Science 2024-03-15 Caroline Choi , Yoonho Lee , Annie Chen , Allan Zhou , Aditi Raghunathan , Chelsea Finn

Software fault localization remains challenging due to limited feature diversity and low precision in traditional methods. This paper proposes a novel approach that integrates multi-objective optimization with deep learning models to…

Software Engineering · Computer Science 2024-11-27 Xiaolei Hu , Dongcheng Li , W. Eric Wong , Ya Zou

Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss functions. This approach has proven effective in aligning Large…

Machine Learning · Computer Science 2024-09-18 Ruoyu Wang , Jiachen Sun , Shaowei Hua , Quan Fang

Federated Learning (FL) enables the utilization of vast, previously inaccessible data sources. At the same time, pre-trained Language Models (LMs) have taken the world by storm and for good reason. They exhibit remarkable emergent abilities…

Machine Learning · Computer Science 2026-05-15 Michael Theologitis , Vasilis Samoladas , Antonios Deligiannakis

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…

Computation and Language · Computer Science 2024-06-27 Shiva Kumar Pentyala , Zhichao Wang , Bin Bi , Kiran Ramnath , Xiang-Bo Mao , Regunathan Radhakrishnan , Sitaram Asur , Na , Cheng

Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use of on-policy data. We propose a framework to bridge this…

Machine Learning · Computer Science 2026-03-17 Miaosen Zhang , Yishan Liu , Shuxia Lin , Xu Yang , Qi Dai , Chong Luo , Weihao Jiang , Peng Hou , Anxiang Zeng , Xin Geng , Baining Guo

Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…

Machine Learning · Computer Science 2026-05-26 Ruiying Peng , Mengyu Yang , Jing Lei , Xiaohui Li , Xueyu Wu , Xinlei Chen

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Machine Learning · Computer Science 2026-04-24 Bingcong Li , Yilang Zhang , Georgios B. Giannakis

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2024-09-10 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Mayank Mishra , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Armand Mihai Nicolicioiu , Andrei Liviu Nicolicioiu , Bogdan Alexe , Damien Teney