English
Related papers

Related papers: Alternate Preference Optimization for Unlearning F…

200 papers

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models in scoring or…

Computation and Language · Computer Science 2025-09-30 Jun Rao , Yunjie Liao , Xuebo Liu , Zepeng Lin , Lian Lian , Dong Jin , Shengjun Cheng , Jun Yu , Min Zhang

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Machine Learning · Computer Science 2025-10-28 Junkang Wu , Kexin Huang , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Computation and Language · Computer Science 2024-12-31 Jingyuan Ma , Rui Li , Zheng Li , Lei Sha , Zhifang Sui

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Computation and Language · Computer Science 2025-05-29 Xiang Huang , Ting-En Lin , Feiteng Fang , Yuchuan Wu , Hangyu Li , Yuzhong Qu , Fei Huang , Yongbin Li

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Machine Learning · Computer Science 2026-02-11 Yuxuan Tang , Yifan Feng

User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgetting" a set of data points from an already-trained model, which…

Machine Learning · Computer Science 2025-07-18 Vaidehi Patil , Elias Stengel-Eskin , Mohit Bansal

Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the…

Computation and Language · Computer Science 2026-04-21 Zeguan Xiao , Lang Mo , Yun Chen , Lei Yang , Jiehui Zhao , Lili Yang , Guanhua Chen

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Computation and Language · Computer Science 2025-10-13 Shi-Qi Yan , Quan Liu , Zhen-Hua Ling

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

Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains are highly impactful.…

Computation and Language · Computer Science 2025-11-18 Ruibo Deng , Duanyu Feng , Wenqiang Lei

Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing…

Computation and Language · Computer Science 2025-03-07 Wenyu Wang , Mengqi Zhang , Xiaotian Ye , Zhaochun Ren , Zhumin Chen , Pengjie Ren

Large Language Models (LLMs) have made significant strides in generating human-like responses, largely due to preference alignment techniques. However, these methods often assume unbiased human feedback, which is rarely the case in…

Machine Learning · Computer Science 2025-09-16 Amirabbas Afzali , Amirhossein Afsharrad , Seyed Shahabeddin Mousavi , Sanjay Lall

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

Machine Learning · Computer Science 2024-07-31 Rafael Rafailov , Archit Sharma , Eric Mitchell , Stefano Ermon , Christopher D. Manning , Chelsea Finn

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Computation and Language · Computer Science 2024-08-09 Tyler Lizzo , Larry Heck

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Computation and Language · Computer Science 2024-05-29 Yueqin Yin , Zhendong Wang , Yi Gu , Hai Huang , Weizhu Chen , Mingyuan Zhou

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

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

Computation and Language · Computer Science 2026-05-28 Yuefeng Peng , Parnian Afshar , Megan Ganji , Thomas Butler , Amir Houmansadr , Mingxian Wang , Dezhi Hong

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means…

Computation and Language · Computer Science 2024-03-28 Dongfang Li , Zetian Sun , Baotian Hu , Zhenyu Liu , Xinshuo Hu , Xuebo Liu , Min Zhang

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

Computation and Language · Computer Science 2025-08-12 Xiaojian Yuan , Tianyu Pang , Chao Du , Kejiang Chen , Weiming Zhang , Min Lin

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward…

Computation and Language · Computer Science 2025-07-29 Tong Liu , Xiao Yu , Wenxuan Zhou , Jindong Gu , Volker Tresp