English
Related papers

Related papers: Constrain Alignment with Sparse Autoencoders

200 papers

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the…

Computation and Language · Computer Science 2025-10-09 Shangjian Yin , Zhepei Wei , Xinyu Zhu , Wei-Lin Chen , Yu Meng

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

Despite advances in pretraining with extended context lengths, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by…

Computation and Language · Computer Science 2025-10-14 Huashan Sun , Shengyi Liao , Yansen Han , Yu Bai , Yang Gao , Cheng Fu , Weizhou Shen , Fanqi Wan , Ming Yan , Ji Zhang , Fei Huang

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

Machine Learning · Computer Science 2025-04-21 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jiawei Chen , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization…

Computation and Language · Computer Science 2024-07-22 Ahmed Allam

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…

Computation and Language · Computer Science 2025-06-06 Wen Yang , Junhong Wu , Chen Wang , Chengqing Zong , Jiajun Zhang

The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences.…

Artificial Intelligence · Computer Science 2026-01-28 Zetian Sun , Dongfang Li , Xuhui Chen , Baotian Hu , Min Zhang

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Computation and Language · Computer Science 2024-02-28 Feifan Song , Bowen Yu , Minghao Li , Haiyang Yu , Fei Huang , Yongbin Li , Houfeng Wang

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Machine Learning · Computer Science 2026-05-18 Yue Wang , Qizhou Wang , Zizhuo Zhang , Gang Niu , Bo Han , Masashi Sugiyama

Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority.…

Computation and Language · Computer Science 2025-03-17 Yafei Zhang , Murray Wang , Yu Wang , Xiaohui Wang

We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward model. SPO optimizes model outputs directly over a…

Machine Learning · Computer Science 2024-10-07 Arsalan Sharifnassab , Saber Salehkaleybar , Sina Ghiassian , Surya Kanoria , Dale Schuurmans

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Machine Learning · Computer Science 2026-05-18 Xiaoqiang Lin , Arun Verma , Zhongxiang Dai , Daniela Rus , See-Kiong Ng , Bryan Kian Hsiang Low

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Machine Learning · Computer Science 2025-06-19 Xuerui Su , Shufang Xie , Guoqing Liu , Yingce Xia , Renqian Luo , Peiran Jin , Zhiming Ma , Yue Wang , Zun Wang , Yuting Liu

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…

Computation and Language · Computer Science 2024-10-08 Dahyun Kim , Yungi Kim , Wonho Song , Hyeonwoo Kim , Yunsu Kim , Sanghoon Kim , Chanjun Park

While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper…

Artificial Intelligence · Computer Science 2024-10-01 Gihun Lee , Minchan Jeong , Yujin Kim , Hojung Jung , Jaehoon Oh , Sangmook Kim , Se-Young Yun

Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. Despite their success, existing methods…

Computation and Language · Computer Science 2025-07-01 Kyuyoung Kim , Ah Jeong Seo , Hao Liu , Jinwoo Shin , Kimin Lee

Reinforcement learning has become central to post-training large language models, yet dominant algorithms rely on clipping mechanisms that introduce optimization issues at scale, including zero-gradient regions, reward hacking, and training…

Machine Learning · Computer Science 2026-02-02 Ömer Veysel Çağatan , Barış Akgün , Gözde Gül Şahin , Xuandong Zhao

Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable. Alternatives have been proposed to replace PPO or…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Feiteng Fang , Yuelin Bai , Longze Chen , Zhexiang Zhang , Minghuan Tan , Min Yang