ORPO: Monolithic Preference Optimization without Reference Model

• URL: http://arxiv.org/abs/2403.07691v2
• Date: Thu, 14 Mar 2024 07:47:08 GMT
• Title: ORPO: Monolithic Preference Optimization without Reference Model
• Authors: Jiwoo Hong, Noah Lee, James Thorne,
• Abstract summary: We study the crucial role of supervised fine-tuning within the context of preference alignment. We introduce a model-free monolithic odds ratio preference optimization algorithm, ORPO, eliminating the necessity for an additional preference alignment phase. Specifically, fine-tuning Phi-2 (2.7B), Llama-2 (7B), and Mistral (7B) with ORPO on the UltraFeedback surpasses the performance of state-of-the-art language models with more than 7B and 13B parameters.
• Score: 9.53888551630878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 study the crucial role of SFT within the context of preference alignment, emphasizing that a minor penalty for the disfavored generation style is sufficient for preference-aligned SFT. Building on this foundation, we introduce a straightforward and innovative reference model-free monolithic odds ratio preference optimization algorithm, ORPO, eliminating the necessity 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 the 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 with more than 7B and 13B parameters: achieving up to 12.20% on $\text{AlpacaEval}_{2.0}$ (Figure 1), 66.19% on IFEval (instruction-level loose, Table 6), and 7.32 in MT-Bench (Figure 12). We release code and model checkpoints for Mistral-ORPO-$\alpha$ (7B) and Mistral-ORPO-$\beta$ (7B).

Related papers

• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
  Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models. Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
  arXiv  Detail & Related papers  (2024-10-04T04:56:11Z)
• Preference Alignment Improves Language Model-Based TTS [76.70693823683091]
  preference alignment algorithms adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores.
  arXiv  Detail & Related papers  (2024-09-19T01:58:19Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• Comparative Analysis of Different Efficient Fine Tuning Methods of Large Language Models (LLMs) in Low-Resource Setting [0.0]
  We try to push the understanding of different fine-tuning strategies for large language models (LLMs) We compare state-of-the-art methods like vanilla fine-tuning and Pattern-Based Fine-Tuning (PBFT) on pre-trained models across two datasets, COLA and MNLI. Our findings suggest that these alternative strategies can exhibit out-of-domain generalization comparable to that of vanilla FT and PBFT.
  arXiv  Detail & Related papers  (2024-05-21T20:08:52Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation [50.00235162432848]
  We train ALMA models with only 22K parallel sentences and 12M parameters. The resulting model, called ALMA-R, can match or exceed the performance of the WMT competition winners and GPT-4.
  arXiv  Detail & Related papers  (2024-01-16T15:04:51Z)
• Mistral 7B [62.17530433867458]
  Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and automated benchmarks.
  arXiv  Detail & Related papers  (2023-10-10T17:54:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.