English
Related papers

Related papers: Negative Preference Optimization: From Catastrophi…

200 papers

Neural Combinatorial Optimization (NCO) has emerged as a promising approach for NP-hard problems. However, prevailing RL-based methods suffer from low sample efficiency due to sparse rewards and underused solutions. We propose Best-anchored…

Machine Learning · Computer Science 2025-06-03 Zijun Liao , Jinbiao Chen , Debing Wang , Zizhen Zhang , Jiahai Wang

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in…

Computation and Language · Computer Science 2026-04-20 Jixuan Leng , Si Si , Hsiang-Fu Yu , Vinod Raman , Inderjit S. Dhillon

Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a beneficial optimization signal. However, these episodes…

Machine Learning · Computer Science 2026-04-03 Dong Shu , Denghui Zhang , Jessica Hullman

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Artificial Intelligence · Computer Science 2025-05-27 Anirudhan Badrinath , Prabhat Agarwal , Jiajing Xu

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask…

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…

Computation and Language · Computer Science 2024-06-04 Pengyu Cheng , Yifan Yang , Jian Li , Yong Dai , Tianhao Hu , Peixin Cao , Nan Du , Xiaolong Li

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Machine Learning · Computer Science 2024-07-01 William Muldrew , Peter Hayes , Mingtian Zhang , David Barber

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradation on retaining…

Machine Learning · Computer Science 2026-02-03 Duo Zhou , Yuji Zhang , Tianxin Wei , Ruizhong Qiu , Ke Yang , Xiao Lin , Cheng Qian , Jingrui He , Hanghang Tong , Chengxiang Zhai , Heng Ji , Huan Zhang

Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization…

Machine Learning · Computer Science 2025-05-07 Zhiqi Bu , Xiaomeng Jin , Bhanukiran Vinzamuri , Anil Ramakrishna , Kai-Wei Chang , Volkan Cevher , Mingyi Hong

Most Video Large Language Models (Video-LLMs) adopt preference alignment techniques, e.g., DPO~\citep{rafailov2024dpo}, to optimize the reward margin between a winning response ($y_w$) and a losing response ($y_l$). However, the likelihood…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Xiaodong Wang , Jinfa Huang , Li Yuan , Peixi Peng

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Software Engineering · Computer Science 2025-12-09 Xin Yin , Chao Ni , Xiaohu Yang

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Cryptography and Security · Computer Science 2025-06-03 Jie Ren , Zhenwei Dai , Xianfeng Tang , Yue Xing , Shenglai Zeng , Hui Liu , Jingying Zeng , Qiankun Peng , Samarth Varshney , Suhang Wang , Qi He , Charu C. Aggarwal , Hui Liu

Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and…

Computation and Language · Computer Science 2026-04-17 Zeguan Xiao , Siqing Li , Yong Wang , Xuetao Wei , Jian Yang , Yun Chen , Guanhua Chen

In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing.…

Computation and Language · Computer Science 2025-07-18 Xinghua Zhang , Haiyang Yu , Cheng Fu , Fei Huang , Yongbin Li

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can…

Computation and Language · Computer Science 2026-03-06 Amirabbas Afzali , Myeongho Jeon , Maria Brbic

As Large Language Models (LLMs) are increasingly deployed in real-world applications, it is important to ensure their behaviors align with human values, societal norms, and ethical principles. However, safety alignment under Reinforcement…

Machine Learning · Computer Science 2026-02-02 Yifan Niu , Han Xiao , Dongyi Liu , Nuo Chen , Jia Li

Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using methods such as LLM unlearning. However, unlearning a set of…

Machine Learning · Computer Science 2026-02-12 Lev McKinney , Anvith Thudi , Juhan Bae , Tara Rezaei , Nicolas Papernot , Sheila A. McIlraith , Roger Grosse
‹ Prev 1 4 5 6 7 8 10 Next ›