English
Related papers

Related papers: What Is Preference Optimization Doing, and Why?

200 papers

Direct Alignment Algorithms (DAAs), such as Direct Preference Optimisation (DPO) and Identity Preference Optimisation (IPO), have emerged as alternatives to online Reinforcement Learning from Human Feedback (RLHF) algorithms such as…

Computation and Language · Computer Science 2024-10-21 Zhengyan Shi , Sander Land , Acyr Locatelli , Matthieu Geist , Max Bartolo

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses equally, neglecting the differing importance of individual…

Computation and Language · Computer Science 2026-05-27 Chengyu Huang , Zhuohang Li , Sheng-Yen Chou , Claire Cardie

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Computation and Language · Computer Science 2025-10-10 Jie Wu , Haoling Li , Xin Zhang , Xiao Liu , Yangyu Huang , Jianwen Luo , Yizhen Zhang , Zuchao Li , Ruihang Chu , Yujiu Yang , Scarlett Li

As large language models (LLMs) see greater use in academic and commercial settings, there is increasing interest in methods that allow language models to generate texts aligned with human preferences. In this paper, we present an initial…

Machine Learning · Computer Science 2024-06-07 Victoria Lin , Eli Ben-Michael , Louis-Philippe Morency

The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preferences can be substituted with pointwise rewards. The second…

Artificial Intelligence · Computer Science 2023-11-23 Mohammad Gheshlaghi Azar , Mark Rowland , Bilal Piot , Daniel Guo , Daniele Calandriello , Michal Valko , Rémi Munos

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Artificial Intelligence · Computer Science 2026-03-25 Shiji Zhao , Mengyang Wang , Shukun Xiong , Fangzhou Chen , Qihui Zhu , Shouwei Ruan , Yisong Xiao , Ranjie Duan , Xun Chen , XingXing Wei

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

Machine Learning · Computer Science 2025-07-22 Junkang Wu , Xue Wang , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs…

Machine Learning · Computer Science 2025-06-23 Yunze Lin

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ziang Yan , Zhilin Li , Yinan He , Chenting Wang , Kunchang Li , Xinhao Li , Xiangyu Zeng , Zilei Wang , Yali Wang , Yu Qiao , Limin Wang , Yi Wang

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for…

Machine Learning · Computer Science 2025-11-19 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers…

Computation and Language · Computer Science 2025-02-21 Ruichen Shao , Bei Li , Gangao Liu , Yang Chen , Xiang Zhou , Jingang Wang , Xunliang Cai , Peng Li

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

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

Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which measure the…

Computation and Language · Computer Science 2025-02-21 Sizhe Wang , Yongqi Tong , Hengyuan Zhang , Dawei Li , Xin Zhang , Tianlong Chen

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair…

Computation and Language · Computer Science 2026-04-13 Chia-Hsuan Lee , Mingyang Zhou , Renkun Ni , Zelei Cheng , Sihui Dai , Supriyo Chakraborty , Shixiong Zhang , Sambit Sahu , William Campbell

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

Computation and Language · Computer Science 2024-09-20 Jinchuan Tian , Chunlei Zhang , Jiatong Shi , Hao Zhang , Jianwei Yu , Shinji Watanabe , Dong Yu

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can…

Computation and Language · Computer Science 2026-03-06 Amirabbas Afzali , Myeongho Jeon , Maria Brbic