English
Related papers

Related papers: Generalizing Reward Modeling for Out-of-Distributi…

200 papers

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Junyong Kang , Seohyun Lim , Kyungjune Baek , Hyunjung Shim

Supervised machine learning often requires human-annotated data. While annotator disagreement is typically interpreted as evidence of noise, population-level label distribution learning (PLDL) treats the collection of annotations for each…

Machine Learning · Computer Science 2021-06-22 Tharindu Cyril Weerasooriya , Tong Liu , Christopher M. Homan

Fine-tuning Large Language Models (LLMs) with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation uses function evaluations instead of gradients, reducing memory usage, but suffers from…

Computation and Language · Computer Science 2025-07-24 Alessio Galatolo , Zhenbang Dai , Katie Winkle , Meriem Beloucif

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei

Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date, such as OpenAI's ChatGPT or Anthropic's Claude. While there has been…

Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on their ability not only to classify in-distribution pixels but…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yuyuan Liu , Choubo Ding , Yu Tian , Guansong Pang , Vasileios Belagiannis , Ian Reid , Gustavo Carneiro

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…

Machine Learning · Computer Science 2026-02-03 Yao Zhao , Kwang-Sung Jun

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between…

Machine Learning · Computer Science 2025-05-27 Chen Jia

Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization, where the preference data is obtained from other models, is…

Computation and Language · Computer Science 2024-10-07 Wenxuan Zhou , Ravi Agrawal , Shujian Zhang , Sathish Reddy Indurthi , Sanqiang Zhao , Kaiqiang Song , Silei Xu , Chenguang Zhu

Predict-then-Optimize (PTO) pipelines are widely employed in computing and networked systems, where Machine Learning (ML) models are used to predict critical contextual information for downstream decision-making tasks such as cloud LLM…

Machine Learning · Computer Science 2026-02-04 Jiaqi Wen , Lei Fan , Jianyi Yang

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose Generalized…

Machine Learning · Computer Science 2023-03-07 Edoardo Cetin , Oya Celiktutan

Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabilities of the underlying large language model (LLM). This…

Machine Learning · Computer Science 2024-08-22 Zachary Ankner , Mansheej Paul , Brandon Cui , Jonathan D. Chang , Prithviraj Ammanabrolu

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Machine Learning · Computer Science 2024-11-13 Chenlu Ye , Wei Xiong , Yuheng Zhang , Hanze Dong , Nan Jiang , Tong Zhang

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribution (OOD) generalization is more common in practice, which…

Machine Learning · Computer Science 2022-02-24 Xin Guo , Zhengxu Yu , Chao Xiang , Zhongming Jin , Jianqiang Huang , Deng Cai , Xiaofei He , Xian-Sheng Hua

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning…

Machine Learning · Computer Science 2026-02-24 Wendi Li , Sharon Li

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Machine Learning · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Xiangyuan Lan , Dongbin Zhao

Semantic communication is a promising technology for next-generation wireless networks. However, the out-of-distribution (OOD) problem, where a pre-trained machine learning (ML) model is applied to unseen tasks that are outside the…

Signal Processing · Electrical Eng. & Systems 2024-07-23 Feifan Zhang , Yuyang Du , Kexin Chen , Yulin Shao , Soung Chang Liew
‹ Prev 1 8 9 10 Next ›