preference optimization

273 papers

Explore in graph

Also known as

ACPO RPO MMPO ORPO KTO DPO SPO PO

Co-occurring keywords

large language model (12755) direct preference optimization (317) reinforcement learning (4122) reinforcement learning from human feedback (261) model alignment (219) language model alignment (142) language model (4573) supervised fine-tuning (310) reward model (251) preference learning (411)

Papers

Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment ACL 2025

DavIR: Data Selection via Implicit Reward for Large Language Models ACL 2025

Sakura at SemEval-2025 Task 2: Enhancing Named Entity Translation with Fine-Tuning and Preference Optimization SEMEVAL 2025

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment NAACL 2025

Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification ACL 2025

DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models ACL 2025

Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning ACL 2025

Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks ACL 2025

RedHit: Adaptive Red-Teaming of Large Language Models via Search, Reasoning, and Preference Optimization ACL 2025

Using LLMs and Preference Optimization for Agreement-Aware HateWiC Classification ACL 2025

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization EMNLP 2025

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models EMNLP 2025

Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts EMNLP 2025

A Comprehensive Survey on Learning from Rewards for Large Language Models: Reward Models and Learning Strategies EMNLP 2025

InFact: Informativeness Alignment for Improved LLM Factuality EMNLP 2025

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization NAACL 2025

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization ACL 2025

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making EMNLP 2025

Enhancing Machine Translation with Self-Supervised Preference Data ACL 2025

PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics NAACL 2025

Evaluating and Aligning Human Economic Risk Preferences in LLMs EMNLP 2025

EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation EMNLP 2025

Enhancing LLM-Based Social Bot via an Adversarial Learning Framework EMNLP 2025

Efficient Long Context Language Model Retrieval with Compression ACL 2025