direct preference optimization

317 papers

Explore in graph

Also known as

DPO

Co-occurring keywords

large language model (12755) preference optimization (273) reinforcement learning from human feedback (261) preference learning (411) language model alignment (142) supervised fine-tuning (310) model alignment (219) preference alignment (142) reinforcement learning (4122) reward model (251)

Papers

RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models NAACL 2024

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model CVPR 2024

A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques ACL 2024

Hybrid Alignment Training for Large Language Models ACL 2024

LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback ACL 2024

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning ACL 2024

Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads NIPS 2024

Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models ACL 2024

BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization ACL 2024

On Softmax Direct Preference Optimization for Recommendation NIPS 2024

A Critical Evaluation of AI Feedback for Aligning Large Language Models NIPS 2024

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation ACL 2024

A General Theoretical Paradigm to Understand Learning from Human Preferences AISTATS 2024

Mercury: A Code Efficiency Benchmark for Code Large Language Models NIPS 2024

Automated Multi-level Preference for MLLMs NIPS 2024

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback NIPS 2024

Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM ACL 2024

SafeWorld: Geo-Diverse Safety Alignment NIPS 2024

$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$ NIPS 2024

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer NIPS 2024

SimPO: Simple Preference Optimization with a Reference-Free Reward NIPS 2024

3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization NIPS 2024

Preference Learning Algorithms Do Not Learn Preference Rankings NIPS 2024

Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain EMNLP 2024

SambaLingo: Teaching Large Language Models New Languages EMNLP 2024