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

Hallucination-Aware Prompt Optimization for Text-to-Video Synthesis IJCAI 2025

NHK Submission to WAT 2025: Leveraging Preference Optimization for Article-level Japanese–English News Translation AACL 2025

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks ACL 2025

Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025

Towards Human Understanding of Paraphrase Types in Large Language Models COLING 2025

Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur COLING 2025

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation COLING 2025

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance EMNLP 2024

Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models COLING 2024

LIONs: An Empirically Optimized Approach to Align Language Models EMNLP 2024

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment EMNLP 2024

Word Alignment as Preference for Machine Translation EMNLP 2024

Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models EMNLP 2024

Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding NAACL 2024

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents NAACL 2024

Improving Socratic Question Generation using Data Augmentation and Preference Optimization NAACL 2024

The Paradox of Preference: A Study on LLM Alignment Algorithms and Data Acquisition Methods NAACL 2024

Direct Multi-Turn Preference Optimization for Language Agents EMNLP 2024

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence EMNLP 2024

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing EMNLP 2024

Automatic Pair Construction for Contrastive Post-training NAACL 2024

ARM: Alignment with Residual Energy-Based Model NAACL 2024

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation ACL 2024

Multi-Modal Hallucination Control by Visual Information Grounding CVPR 2024

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback CVPR 2024