English
Related papers

Related papers: Implicit Regularization in Feedback Alignment Lear…

200 papers

Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the…

Computation and Language · Computer Science 2024-08-13 Mengjie Ren , Boxi Cao , Hongyu Lin , Cao Liu , Xianpei Han , Ke Zeng , Guanglu Wan , Xunliang Cai , Le Sun

We present NPO, an alignment-aware learning framework that operationalizes feedback-driven adaptation in human-in-the-loop decision systems. Unlike prior approaches that treat alignment as a static or post-hoc property, NPO introduces a…

Artificial Intelligence · Computer Science 2025-07-30 Madhava Gaikwad , Ashwini Ramchandra Doke

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Machine Learning · Computer Science 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

Conversational recommender systems (CRS) based on Large Language Models (LLMs) need to constantly be aligned to the user preferences to provide satisfying and context-relevant item recommendations. The traditional supervised fine-tuning…

Machine Learning · Computer Science 2025-08-08 Zhongheng Yang , Aijia Sun , Yushang Zhao , Yinuo Yang , Dannier Li , Chengrui Zhou

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups. Specifically, we formulate this intuition as a bi-level…

Machine Learning · Computer Science 2022-05-27 Changjian Shui , Qi Chen , Jiaqi Li , Boyu Wang , Christian Gagné

Federated learning (FL) triggers intra-client and inter-client class imbalance, with the latter compared to the former leading to biased client updates and thus deteriorating the distributed models. Such a bias is exacerbated during the…

Machine Learning · Computer Science 2024-12-24 Chenguang Xiao , Zheming Zuo , Shuo Wang

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

Computation and Language · Computer Science 2025-10-06 Hangfan Zhang , Siyuan Xu , Zhimeng Guo , Huaisheng Zhu , Shicheng Liu , Xinrun Wang , Qiaosheng Zhang , Yang Chen , Peng Ye , Lei Bai , Shuyue Hu

There were many algorithms to substitute the back-propagation (BP) in the deep neural network (DNN) training. However, they could not become popular because their training accuracy and the computational efficiency were worse than BP. One of…

Machine Learning · Computer Science 2019-01-09 Donghyeon Han , Hoi-jun Yoo

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

Understanding the mechanisms through which neural networks extract statistics from input-label pairs through feature learning is one of the most important unsolved problems in supervised learning. Prior works demonstrated that the gram…

Machine Learning · Statistics 2024-11-19 Daniel Beaglehole , Ioannis Mitliagkas , Atish Agarwala

Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches typically treat all layers uniformly, often trading stability…

Machine Learning · Computer Science 2025-12-29 Hengyi Wu , Zhenyi Wang , Heng Huang

Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and…

Computation and Language · Computer Science 2024-07-08 Miguel Moura Ramos , Patrick Fernandes , António Farinhas , André F. T. Martins

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Machine Learning · Computer Science 2025-03-05 Kexin Huang , Junkang Wu , Ziqian Chen , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

In recent years, understanding the implicit regularization of neural networks (NNs) has become a central task in deep learning theory. However, implicit regularization is itself not completely defined and well understood. In this work, we…

Machine Learning · Computer Science 2023-09-08 Leyang Zhang , Zhi-Qin John Xu , Tao Luo , Yaoyu Zhang

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Machine Learning · Computer Science 2024-02-05 Nathan Lambert , Roberto Calandra

To mitigate reward hacking from response verbosity, modern preference optimization methods are increasingly adopting length normalization (e.g., SimPO, ORPO, LN-DPO). While effective against this bias, we demonstrate that length…

Machine Learning · Computer Science 2025-11-06 Taneesh Gupta , Rahul Madhavan , Xuchao Zhang , Chetan Bansal , Saravan Rajmohan

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto
‹ Prev 1 4 5 6 7 8 10 Next ›