Skip to content
conftrace_

preference optimization

355 papers

Explore in graph

Also known as

PO

Co-occurring keywords · papers mentioning both

large language model (156) direct preference optimization (50) reinforcement learning (44) reinforcement learning from human feedback (36) language model alignment (31) model alignment (30) language model (29) supervised fine-tuning (29) reward model (23) diffusion model (18)

Papers

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters ICLR 2025 Slamming: Training a Speech Language Model on One GPU in a Day ACL 2025 SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization CVPR 2025 Spatial Preference Rewarding for MLLMs Spatial Understanding ICCV 2025 SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin EMNLP 2025 Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment ICML 2025 Structured Policy Optimization: Enhance Large Vision-Language Model via Self-referenced Dialogue ICCV 2025 Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking ICLR 2025 Style Transfer with Multi-iteration Preference Optimization NAACL 2025 Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization ICLR 2025 SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization CVPR 2025 TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making EMNLP 2025 Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences ACL 2025 Teaching Models to Balance Resisting and Accepting Persuasion NAACL 2025 The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation ACL 2025 Thinking LLMs: General Instruction Following with Thought Generation ICML 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 Token-level Preference Self-Alignment Optimization for Multi-style Outline Controllable Generation ACL 2025 Training Language Model to Critique for Better Refinement ACL 2025 TRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data ACL 2025 T-REG: Preference Optimization with Token-Level Reward Regularization ACL 2025 Tuning Less, Prompting More: In-Context Preference Learning Pipeline for Natural Language Transformation EMNLP 2025 Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization ICLR 2025 Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time EMNLP 2025 Uncertainty-Aware Iterative Preference Optimization for Enhanced LLM Reasoning ACL 2025