English
Related papers

Related papers: Knowledge Editing in Language Models via Adapted D…

200 papers

Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing techniques exhibit…

Computation and Language · Computer Science 2024-08-23 Mengqi Zhang , Bowen Fang , Qiang Liu , Pengjie Ren , Shu Wu , Zhumin Chen , Liang Wang

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

As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing…

Computation and Language · Computer Science 2024-12-31 Yongchang Li , Yujin Zhu , Tao Yan , Shijian Fan , Gang Wu , Liang Xu

We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…

Machine Learning · Computer Science 2026-01-13 Wang Zixian

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

Computation and Language · Computer Science 2024-06-18 Jie Liu , Zhanhui Zhou , Jiaheng Liu , Xingyuan Bu , Chao Yang , Han-Sen Zhong , Wanli Ouyang

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

Machine Learning · Computer Science 2025-05-14 Teng Xiao , Zhen Ge , Sujay Sanghavi , Tian Wang , Julian Katz-Samuels , Marc Versage , Qingjun Cui , Trishul Chilimbi

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses equally, neglecting the differing importance of individual…

Computation and Language · Computer Science 2026-05-27 Chengyu Huang , Zhuohang Li , Sheng-Yen Chou , Claire Cardie

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Minpeng Liao , Chengxi Li , Kai Fan

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific…

Machine Learning · Computer Science 2025-10-07 Kai Qin , Jiaqi Wu , Jianxiang He , Haoyuan Sun , Yifei Zhao , Bin Liang , Yongzhe Chang , Tiantian Zhang , Houde Liu

While prompt optimization has emerged as a critical technique for enhancing language model performance, existing approaches primarily focus on elicitation-based strategies that search for optimal prompts to activate models' capabilities.…

Computation and Language · Computer Science 2026-03-31 Yunzhe Xu , Zhuosheng Zhang , Zhe Liu

Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizing self-generated synthetic data has become crucial for…

Computation and Language · Computer Science 2026-03-17 Haoyan Yang , Khiem Le , Ting Hua , Shangqian Gao , Binfeng Xu , Zheng Tang , Jie Xu , Nitesh V. Chawla , Hongxia Jin , Vijay Srinivasan

Pretrained Language Models (PLMs) store extensive knowledge within their weights, enabling them to recall vast amount of information. However, relying on this parametric knowledge brings some limitations such as outdated information or gaps…

Computation and Language · Computer Science 2024-06-18 Alessio Galatolo , Meriem Beloucif , Katie Winkle

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the…

Computation and Language · Computer Science 2025-05-29 Tianci Liu , Ruirui Li , Zihan Dong , Hui Liu , Xianfeng Tang , Qingyu Yin , Linjun Zhang , Haoyu Wang , Jing Gao

Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has emerged as a potent…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Dain Kim , Jiwoo Lee , Jaehoon Yun , Yong Hoe Koo , Qingyu Chen , Hyunjae Kim , Jaewoo Kang

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Artificial Intelligence · Computer Science 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as \textbf{learning-dynamics--aware optimization} and…

Machine Learning · Computer Science 2025-10-15 Jusheng Zhang , Kaitong Cai , Jing Yang , Keze Wang

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

Reinforcement learning from human feedback (RLHF) plays a crucial role in aligning language models with human preferences. While the significance of dataset quality is generally recognized, explicit investigations into its impact within the…

Machine Learning · Computer Science 2024-12-04 Tetsuro Morimura , Mitsuki Sakamoto , Yuu Jinnai , Kenshi Abe , Kaito Ariu