English
Related papers

Related papers: Unintentional Unalignment: Likelihood Displacement…

200 papers

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Artificial Intelligence · Computer Science 2026-05-21 Zhiqin Yang , Yonggang Zhang , Wei Xue , Dong Fang , Bo Han , Yike Guo

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

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Machine Learning · Computer Science 2026-01-27 Saeed Najafi , Alona Fyshe

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

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Computation and Language · Computer Science 2026-05-19 Xuan Qi , Rongwu Xu , Zhijing Jin

Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…

Machine Learning · Computer Science 2024-10-31 Jae Hyeon Cho , Minkyung Park , Byung-Jun Lee

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Computation and Language · Computer Science 2026-02-26 Ruochen Mao , Yuling Shi , Xiaodong Gu , Jiaheng Wei

Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training stability. However, DPO suffers from the recently identified…

Machine Learning · Computer Science 2026-03-20 Haocheng Luo , Zehang Deng , Thanh-Toan Do , Mehrtash Harandi , Dinh Phung , Trung Le

Quality of datasets plays an important role in large language model (LLM) alignment. In collecting human feedback, however, preference flipping is ubiquitous and causes corruption in data annotation; the issue necessitates the alignment…

Artificial Intelligence · Computer Science 2025-12-02 Yifan Xu , Xichen Ye , Yifan Chen , Qiaosheng Zhang

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

We study the problem of aligning large language models (LLMs) with human preference data. Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward…

Machine Learning · Computer Science 2024-12-20 Teng Xiao , Yige Yuan , Huaisheng Zhu , Mingxiao Li , Vasant G Honavar

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…

Machine Learning · Computer Science 2026-02-04 Maksim Afanasyev , Illarion Iov

Direct Preference Optimization (DPO) has been proposed as a promising alternative to Proximal Policy Optimization (PPO) based Reinforcement Learning with Human Feedback (RLHF). However, empirical evaluations consistently reveal suboptimal…

Machine Learning · Computer Science 2025-03-03 Qinwei Ma , Jingzhe Shi , Can Jin , Jenq-Neng Hwang , Serge Belongie , Lei Li

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the…

Computation and Language · Computer Science 2025-05-14 Binwei Yao , Zefan Cai , Yun-Shiuan Chuang , Shanglin Yang , Ming Jiang , Diyi Yang , Junjie Hu

Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) by learning from preference pairs. One of its key challenges lies in how to transfer the…

Machine Learning · Computer Science 2026-05-07 Huatian Zhang , Zhendong Mao , Lei Zhang , Yongdong Zhang

The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with…

Computation and Language · Computer Science 2024-06-06 Haozhe Ji , Cheng Lu , Yilin Niu , Pei Ke , Hongning Wang , Jun Zhu , Jie Tang , Minlie Huang

Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference…

Computation and Language · Computer Science 2024-06-10 Michael J. Ryan , William Held , Diyi Yang

Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy.…

Machine Learning · Computer Science 2024-12-02 Wei Liu , Yang Bai , Chengcheng Han , Rongxiang Weng , Jun Xu , Xuezhi Cao , Jingang Wang , Xunliang Cai

Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, existing work rarely examines how Direct Preference…

Information Retrieval · Computer Science 2026-04-01 Hejin Huang , Jusheng Zhang , Kaitong Cai , Jian Wang , Rong Pan
‹ Prev 1 3 4 5 6 7 10 Next ›