English
Related papers

Related papers: Mind the Gap: Data Rewriting for Stable Off-Policy…

200 papers

Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SELF-JUDGE that (1)…

Machine Learning · Computer Science 2024-06-26 Sangkyu Lee , Sungdong Kim , Ashkan Yousefpour , Minjoon Seo , Kang Min Yoo , Youngjae Yu

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Meng Lou , Hanzhong Guo , Linwei Chen , Yizhou Yu

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). SFT advocates for the fine-tuning of DDPM samplers through…

Machine Learning · Computer Science 2024-09-23 Ying Fan , Kangwook Lee

Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is…

Computation and Language · Computer Science 2024-07-24 Xiou Ge , Ali Mousavi , Edouard Grave , Armand Joulin , Kun Qian , Benjamin Han , Mostafa Arefiyan , Yunyao Li

Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…

Computation and Language · Computer Science 2025-10-20 Chenxing Wei , Yao Shu , Mingwen Ou , Ying Tiffany He , Fei Richard Yu

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

Computation and Language · Computer Science 2023-05-01 George Pu , Anirudh Jain , Jihan Yin , Russell Kaplan

Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of Large Language Models (LLMs) to various downstream applications. However, the effectiveness of the PEFT diminishes notably when downstream tasks require accurate…

Computation and Language · Computer Science 2024-05-29 Renzhi Wang , Piji Li

A prevailing view holds that supervised fine-tuning (SFT) memorizes training data and fails to generalize, whereas reinforcement learning (RL) attains broader robustness. We revisit this claim through a systematic evaluation on two…

Machine Learning · Computer Science 2025-10-02 Xiaofeng Lin , Hejian Sang , Zhipeng Wang , Xuezhou Zhang

Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting general knowledge. We…

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the accessible data size and…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yuxin Tian , Mouxing Yang , Yunfan Li , Dayiheng Liu , Xingzhang Ren , Xi Peng , Jiancheng Lv

Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Reza Akbarian Bafghi , Carden Bagwell , Avinash Ravichandran , Ashish Shrivastava , Maziar Raissi

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits…

Artificial Intelligence · Computer Science 2026-03-04 Siwei Wang , Yifei Shen , Haoran Sun , Shi Feng , Shang-Hua Teng , Li Dong , Yaru Hao , Wei Chen

Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…

Computation and Language · Computer Science 2023-12-29 Yang Xu , Yongqiang Yao , Yufan Huang , Mengnan Qi , Maoquan Wang , Bin Gu , Neel Sundaresan

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Machine Learning · Computer Science 2025-10-07 Lianghuan Huang , Sagnik Anupam , Insup Lee , Shuo Li , Osbert Bastani

Finetuning language models for a new domain inevitably leads to the deterioration of their general performance. This becomes more pronounced the more limited the finetuning data resource. We introduce minifinetuning (MFT), a method for…

Machine Learning · Computer Science 2025-06-23 Peter Belcak , Greg Heinrich , Jan Kautz , Pavlo Molchanov

Sample selection is an effective strategy to mitigate the effect of label noise in robust learning. Typical strategies commonly apply the small-loss criterion to identify clean samples. However, those samples lying around the decision…

Computer Vision and Pattern Recognition · Computer Science 2022-08-25 Qi Wei , Haoliang Sun , Xiankai Lu , Yilong Yin

Unstructured Knowledge Editing (UKE) is crucial for updating the relevant knowledge of large language models (LLMs). It focuses on unstructured inputs, such as long or free-form texts, which are common forms of real-world knowledge.…

Computation and Language · Computer Science 2025-06-12 Hao Xiong , Chuanyuan Tan , Wenliang Chen

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Machine Learning · Computer Science 2025-10-13 Lixuan He , Jie Feng , Yong Li
‹ Prev 1 8 9 10 Next ›