ORPO: Monolithic Preference Optimization without Reference Model

Jiwoo Hong, Noah Lee, James Thorne


Abstract
While recent preference alignment algorithms for language models have demonstrated promising results, supervised fine-tuning (SFT) remains imperative for achieving successful convergence. In this paper, we revisit SFT in the context of preference alignment, emphasizing that a minor penalty for the disfavored style is sufficient for preference alignment. Building on this foundation, we introduce a straightforward reference model-free monolithic odds ratio preference optimization algorithm, ORPO, eliminating the need for an additional preference alignment phase. We demonstrate, both empirically and theoretically, that the odds ratio is a sensible choice for contrasting favored and disfavored styles during SFT across diverse sizes from 125M to 7B. Specifically, fine-tuning Phi-2 (2.7B), Llama-2 (7B), and Mistral (7B) with ORPO on the UltraFeedback alone surpasses the performance of state-of-the-art language models including Llama-2 Chat and Zephyr with more than 7B and 13B parameters: achieving up to 12.20% on AlpacaEval 2.0 (Figure 1), and 7.32 in MT-Bench (Table 2). We release code and model checkpoints for Mistral-ORPO-𝛼 (7B) and Mistral-ORPO-𝛽 (7B).
Anthology ID:
2024.emnlp-main.626
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11170–11189
Language:
URL:
https://aclanthology.org/2024.emnlp-main.626
DOI:
10.18653/v1/2024.emnlp-main.626
Bibkey:
Cite (ACL):
Jiwoo Hong, Noah Lee, and James Thorne. 2024. ORPO: Monolithic Preference Optimization without Reference Model. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11170–11189, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
ORPO: Monolithic Preference Optimization without Reference Model (Hong et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.626.pdf
Software:
 2024.emnlp-main.626.software.zip