preference alignment

142 papers

Explore in graph

Also known as

DPO

Co-occurring keywords

large language model (12755) direct preference optimization (317) reinforcement learning from human feedback (261) reinforcement learning (4122) reward model (251) reward modeling (159) preference optimization (273) language model alignment (142) instruction tuning (810) language model (4573)

Papers

Self-Generated Critiques Boost Reward Modeling for Language Models NAACL 2025

Alignment with Fill-In-the-Middle for Enhancing Code Generation EMNLP 2025

FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data EMNLP 2025

Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety EMNLP 2025

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion EMNLP 2025

A Recipe For Building a Compliant Real Estate Chatbot COLING 2025

Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks ACL 2025

Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator NAACL 2025

DPL: Diverse Preference Learning Without A Reference Model NAACL 2025

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM ICCV 2025

Instantly Learning Preference Alignment via In-context DPO NAACL 2025

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning ACL 2025

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key CVPR 2025

Synergistic Weak-Strong Collaboration by Aligning Preferences ACL 2025

What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning AAAI 2025

Self-Augmented Preference Alignment for Sycophancy Reduction in LLMs EMNLP 2025

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment COLING 2025

RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data AAAI 2025

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment ACL 2025

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization ACL 2025

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations EMNLP 2025

Benchmarking and Improving LLM Robustness for Personalized Generation EMNLP 2025

TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation EMNLP 2025

Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering COLING 2025