English
Related papers

Related papers: Meta-Learning Objectives for Preference Optimizati…

200 papers

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…

Machine Learning · Computer Science 2017-05-31 Joshua Achiam , David Held , Aviv Tamar , Pieter Abbeel

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

Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models…

Machine Learning · Computer Science 2025-06-10 Qi Liu , Jingqing Ruan , Hao Li , Haodong Zhao , Desheng Wang , Jiansong Chen , Wan Guanglu , Xunliang Cai , Zhi Zheng , Tong Xu

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

We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization…

Optimization and Control · Mathematics 2022-06-13 Anatoli Juditsky , Joon Kwon , Éric Moulines

Large Language Models (LLMs) often memorize sensitive, private, or copyrighted data during pre-training. LLM unlearning aims to eliminate the influence of undesirable data from the pre-trained model while preserving the model's utilities on…

Machine Learning · Computer Science 2024-10-14 Ruiqi Zhang , Licong Lin , Yu Bai , Song Mei

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models (LLMs) with human preferences, bypassing the need for a learned reward model. Despite its growing adoption, a fundamental…

Machine Learning · Computer Science 2025-11-10 Yu Pan , Zhongze Cai , Guanting Chen , Huaiyang Zhong , Chonghuan Wang

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

Machine Learning · Computer Science 2024-03-06 Zixuan Liu , Xiaolin Sun , Zizhan Zheng

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…

Machine Learning · Computer Science 2025-10-10 Chenxi Liu , Tianyi Xiong , Yanshuo Chen , Ruibo Chen , Yihan Wu , Junfeng Guo , Tianyi Zhou , Heng Huang

Effective training of language models (LMs) for mathematical reasoning tasks demands high-quality supervised fine-tuning data. Besides obtaining annotations from human experts, a common alternative is sampling from larger and more powerful…

Computation and Language · Computer Science 2024-07-26 Tianduo Wang , Shichen Li , Wei Lu

Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO,…

Machine Learning · Computer Science 2024-02-27 Ziniu Li , Tian Xu , Yang Yu

Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream…

Computation and Language · Computer Science 2026-04-03 Yuhang Wu , Xiangqing Shen , Fanfan Wang , Cangqi Zhou , Zhen Wu , Xinyu Dai , Rui Xia

Multimodal large language models (MLLMs) have achieved remarkable success across various tasks. However, separate training of visual and textual encoders often results in a misalignment of the modality. Such misalignment may lead models to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Songtao Jiang , Yan Zhang , Ruizhe Chen , Tianxiang Hu , Yeying Jin , Qinglin He , Yang Feng , Jian Wu , Zuozhu Liu

While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper…

Artificial Intelligence · Computer Science 2024-10-01 Gihun Lee , Minchan Jeong , Yujin Kim , Hojung Jung , Jaehoon Oh , Sangmook Kim , Se-Young Yun

In this work we propose MirrorCBO, a consensus-based optimization (CBO) method which generalizes standard CBO in the same way that mirror descent generalizes gradient descent. For this we apply the CBO methodology to a swarm of dual…

Optimization and Control · Mathematics 2025-07-17 Leon Bungert , Franca Hoffmann , Dohyeon Kim , Tim Roith

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Computation and Language · Computer Science 2025-03-04 Yuxuan Liu

Direct Preference Optimization (DPO) and its variants have become standard for aligning Large Language Models due to their simplicity and offline stability. However, we identify two fundamental limitations. First, the optimal policy depends…

Artificial Intelligence · Computer Science 2026-02-10 Yu Li , Tian Lan , Zhengling Qi

In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we…

Machine Learning · Computer Science 2024-08-13 Yiyang Zhao , Linnan Wang , Kevin Yang , Tianjun Zhang , Tian Guo , Yuandong Tian

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