paper-with-me

Papers

ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation

2025-09-29 · Aasheesh Singh, Vishal Vaddina, Dagnachew Birru arxiv

We introduce ORPO-Distill, a general-purpose method for cross-architecture LLM distillation that formulates the problem as a preference optimization task. Unlike standard CoT distillation, the approach transfers knowledge through diverse reasoning traces. It employs an Odds-Ratio Preference Optimization objective that contrasts teacher and student traces for more effective learning, and adopts a mixed-policy strategy for utilizing student-generated outputs, outperforming both off- and on-policy alternatives. Experiments on five datasets and multiple student models show consistent improvements over conventional black-box KD baselines.

📄 PDF Abstract BibTeX arXiv:2509.25100

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Online Knowledge Distillation with Reward Guidance

2025-05-25 · Chen Jia

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimizatio…

Imitation LearningKnowledge Distillation

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

2026-05-11 · Siqi Zhu, Xuyan Ye, Hongyu Lu, Weiye Shi 외 arxiv

On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offering dense token-level supervision on trajectories sampled from the model…

Mathematical Reasoning

Learning Loss Landscapes in Preference Optimization

2024-11-10 · Carlo Alfano, Silvia Sapora, Jakob Nicolaus Foerster, Patrick Rebeschini 외

We present an empirical study investigating how specific properties of preference datasets, such as mixed-quality or noisy data, affect the performance of Preference Optimization (PO) algorithms. Our experiments, conduct…

MuJoCo

Preference as Reward, Maximum Preference Optimization with Importance Sampling

2023-12-27 · Zaifan Jiang, Xing Huang, Chao Wei

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a rew…

KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQA

2026-01-30 · Fan Yang, Rui Meng, Trudi Di Qi, Ali Ezzati 외 arxiv

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally c…

Visual Question AnsweringReinforcement LearningMultimodal Reasoning