Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
DPO
Description:
Direct Preference Optimization is a method for aligning language models by training them on preference comparisons without a separate reward model.
Related topics:
Topic Modeling (18%),
Reinforcement Learning in Robotics (8%),
Natural Language Processing Techniques (7%)
Wikidata ID:
wiki/Q139833558
OpenAlex ID:
keywords/dpo
KTO: Model Alignment as Prospect Theoretic Optimization
2024
·
Ethayarajh, Kawin
, Xu, Winnie
, et al.
·
arXiv (Cornell University)
·
1,228
PDF
AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
2023
·
Yann Dubois
, Chen Xuechen Li
, et al.
·
neural information processing systems
·
1,076
Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
2023
·
Ivison, Hamish
, Wang, Yizhong
, et al.
·
arXiv (Cornell University)
·
410
PDF
Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities
2025
·
Mohamed Amine Ferrag
, Fatima Alwahedi
, et al.
·
Internet of Things and Cyber-Physical Systems
·
401
Direct Language Model Alignment from Online AI Feedback
2024
·
Guo, Shangmin
, Zhang, Biao
, et al.
·
arXiv (Cornell University)
·
345
PDF
V-STaR: Training Verifiers for Self-Taught Reasoners
2024
·
Hosseini, Arian
, Yuan, Xingdi
, et al.
·
Edinburgh Research Explorer (University of Edinburgh)
·
321
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents
2024
·
Yifan Song
, Da Yin
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
312
PDF
Self-Play Preference Optimization for Language Model Alignment
2025
·
Wu, Yue
, Sun, Zhiqing
, et al.
·
International Conference on Learning Representations
·
249
PDF
Generalized Preference Optimization: A Unified Approach to Offline Alignment
2024
·
Tang, Yunhao
, Guo, Zhaohan Daniel
, et al.
·
arXiv (Cornell University)
·
176
PDF
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
2024
·
Hamish Ivison
, Yizhong Wang
, et al.
·
neural information processing systems
·
165
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
2024
·
Lin Gui
, Cristina Gârbacea
, et al.
·
neural information processing systems
·
155
Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
2024
·
Wei, Hui
, He, Shenghua
, et al.
·
arXiv (Cornell University)
·
120
PDF
Consensus mechanism for software-defined blockchain in internet of things
2022
·
Ruihang Huang
, Xiaoming Yang
, et al.
·
Internet of Things and Cyber-Physical Systems
·
98
Making Large Language Models Better Reasoners with Alignment
2023
·
Wang, Peiyi
, Li, Lei
, et al.
·
arXiv (Cornell University)
·
95
PDF
Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance
2025
·
Qian, Lingfei
, Zhou, Weipeng
, et al.
·
arXiv (Cornell University)
·
91
PDF
Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective
2024
·
Feng, Duanyu
, Qin, Bowen
, et al.
·
arXiv (Cornell University)
·
91
PDF
Three autoinducer molecules act in concert to control virulence gene expression in Vibrio cholerae
2019
·
Roman Herzog
, Nikolai Peschek
, et al.
·
Nucleic Acids Research
·
91
PDF
LiPO: Listwise Preference Optimization through Learning-to-Rank
2024
·
Liu, Tianqi
, Qin, Zhen
, et al.
·
arXiv (Cornell University)
·
89
PDF
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
2025
·
Sagnik Mukherjee
, Lifan Yuan
, et al.
·
neural information processing systems
·
81
A New Election Algorithm for DPos Consensus Mechanism in Blockchain
2018
·
Yinghui Luo
, Yiqun Chen
, et al.
·
International Conference on Digital Home (ICDH)
·
81
CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
2024
·
Yassine Ouali
, Adrian Bulat
, et al.
·
Lecture notes in computer science
·
76
PDF
Preference Learning Algorithms Do Not Learn Preference Rankings
2024
·
Angelica Chen
, Sadhika Malladi
, et al.
·
neural information processing systems
·
69
Evaluating the Diversity and Quality of LLM Generated Content
2025
·
Shypula, Alexander
, Li, Shuo
, et al.
·
arXiv (Cornell University)
·
65
PDF
Model Extrapolation Expedites Alignment
2025
·
Chujie Zheng
, Ziqi Wang
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
63
PDF
Blockchain Empowered Wireless Power Transfer for Green and Secure Internet of Things
2019
·
Li Jiang
, Shengli Xie
, et al.
·
IEEE Network
·
60
Show more works
View as search
Works count:
545
Citation count:
8,281
Year
Topic
Type