English
Related papers

Related papers: Curriculum Learning for Safety Alignment

200 papers

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

Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives…

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Machine Learning · Computer Science 2024-08-08 Shashank Gupta , Harrie Oosterhuis , Maarten de Rijke

Direct Preference Optimization (DPO) is a principled, scalable alternative to RLHF for aligning large language models from pairwise preferences, but its internal geometric footprint remains undercharacterized, limiting audits, checkpoint…

Machine Learning · Computer Science 2026-01-13 Arion Das , Partha Pratim Saha , Amit Dhanda , Vinija Jain , Aman Chadha , Amitava Das

Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicity and effectiveness. However, existing methods typically…

Computation and Language · Computer Science 2024-10-28 Shilong Li , Yancheng He , Hui Huang , Xingyuan Bu , Jiaheng Liu , Hangyu Guo , Weixun Wang , Jihao Gu , Wenbo Su , Bo Zheng

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Computation and Language · Computer Science 2025-05-27 Yeyuan Wang , Dehong Gao , Rujiao Long , Lei Yi , Linbo Jin , Libin Yang , Xiaoyan Cai

Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning, one of the most popular approaches, stands out for its efficiency in reward modeling.…

Machine Learning · Computer Science 2026-05-26 Xiaobo Wang , Zixia Jia , Jiaqi Li , Qi Liu , Zilong Zheng

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

Machine Learning · Computer Science 2026-02-03 Mete Erdogan

Recent advances in Emotional Support Conversation (ESC) have improved emotional support generation by fine-tuning Large Language Models (LLMs) via Supervised Fine-Tuning (SFT). However, common psychological errors still persist. While…

Computation and Language · Computer Science 2026-01-19 Chao Zhang , Xin Shi , Xueqiao Zhang , Yifan Zhu , Yi Yang , Yawei Luo

It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…

Computation and Language · Computer Science 2025-06-03 Qingyu Ren , Jie Zeng , Qianyu He , Jiaqing Liang , Yanghua Xiao , Weikang Zhou , Zeye Sun , Fei Yu

Multi-objective reinforcement learning (MORL) seeks to learn policies that balance multiple, often conflicting objectives. Although a single preference-conditioned policy is the most flexible and scalable solution, existing approaches…

Machine Learning · Computer Science 2026-02-10 Tanmay Ambadkar , Sourav Panda , Shreyash Kale , Jonathan Dodge , Abhinav Verma

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

Machine Learning · Computer Science 2026-05-21 Shengfan Cao , Francesco Borrelli , Eunhyek Joa

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Khiem Pham , Quang Nguyen , Tung Nguyen , Jingsen Zhu , Michele Santacatterina , Dimitris Metaxas , Ramin Zabih

In an era of rampant misinformation, generating reliable news explanations is vital, especially for under-represented languages like Hindi. Lacking robust automated tools, Hindi faces challenges in scaling misinformation detection. To…

Computation and Language · Computer Science 2026-04-21 Pulkit Bansal , Raghvendra Kumar , Shakti Singh , Adam Jatowt , Sriparna Saha

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an…

Artificial Intelligence · Computer Science 2025-07-15 Wenyi Xiao , Zechuan Wang , Leilei Gan , Shuai Zhao , Zongrui Li , Ruirui Lei , Wanggui He , Luu Anh Tuan , Long Chen , Hao Jiang , Zhou Zhao , Fei Wu

The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an efficient method that directly optimizes models using…

Computation and Language · Computer Science 2025-10-30 Jie Sun , Junkang Wu , Jiancan Wu , Zhibo Zhu , Xingyu Lu , Jun Zhou , Lintao Ma , Xiang Wang

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

Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect…

Machine Learning · Computer Science 2025-05-20 Wenya Guo , Zhengkun Zhang , Xumeng Liu , Ying Zhang , Ziyu Lu , Haoze Zhu , Xubo Liu , Ruxue Yan