English
Related papers

Related papers: Efficient Safety Retrofitting Against Jailbreaking…

200 papers

Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when…

Computation and Language · Computer Science 2024-07-15 Xiangkun Hu , Tong He , David Wipf

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

Computation and Language · Computer Science 2025-04-30 Kian Ahrabian , Xihui Lin , Barun Patra , Vishrav Chaudhary , Alon Benhaim , Jay Pujara , Xia Song

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

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

Computation and Language · Computer Science 2025-03-10 Changyu Chen , Zichen Liu , Chao Du , Tianyu Pang , Qian Liu , Arunesh Sinha , Pradeep Varakantham , Min Lin

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Computation and Language · Computer Science 2024-09-27 Jian Li , Haojing Huang , Yujia Zhang , Pengfei Xu , Xi Chen , Rui Song , Lida Shi , Jingwen Wang , Hao Xu

Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable…

Artificial Intelligence · Computer Science 2025-04-29 Qizhang Feng , Siva Rajesh Kasa , Santhosh Kumar Kasa , Hyokun Yun , Choon Hui Teo , Sravan Babu Bodapati

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

Safety fine-tuning algorithms reduce harmful outputs in language models, yet their mechanisms remain under-explored. Direct Preference Optimization (DPO) is a popular choice of algorithm, but prior explanations, attributing its effects…

Machine Learning · Computer Science 2025-06-10 Yushi Yang , Filip Sondej , Harry Mayne , Andrew Lee , Adam Mahdi

Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset. However, DPO has the limitation that the KL penalty, which prevents excessive deviation…

Machine Learning · Computer Science 2025-10-28 Sangkyu Lee , Janghoon Han , Hosung Song , Stanley Jungkyu Choi , Honglak Lee , Youngjae Yu

Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse preference data, causing…

Machine Learning · Computer Science 2025-10-08 Hyung Gyu Rho

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…

Computation and Language · Computer Science 2026-03-03 Aladin Djuhera , Farhan Ahmed , Swanand Ravindra Kadhe , Syed Zawad , Heiko Ludwig , Holger Boche

Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributionally. In this work,…

Machine Learning · Computer Science 2024-12-31 Hiroki Furuta , Kuang-Huei Lee , Shixiang Shane Gu , Yutaka Matsuo , Aleksandra Faust , Heiga Zen , Izzeddin Gur

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

Machine Learning · Computer Science 2025-05-20 Wenqiao Zhu , Ji Liu , Lulu Wang , Jun Wu , Yulun Zhang

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

Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy generation typically yields multiple candidate responses…

Machine Learning · Computer Science 2025-06-23 Taneesh Gupta , Rahul Madhavan , Xuchao Zhang , Nagarajan Natarajan , Chetan Bansal , Saravan Rajmohan

When fine-tuning pre-trained Large Language Models (LLMs) to align with human values and intentions, maximizing the estimated reward can lead to superior performance, but it also introduces potential risks due to deviations from the…

Machine Learning · Computer Science 2025-05-30 Lijun Zhang , Lin Li , Yajie Qi , Huizhong Song , Yaodong Yang , Jun Wang , Wei Wei
‹ Prev 1 3 4 5 6 7 10 Next ›