Minor DPO reject penalty to increase training robustness

• URL: http://arxiv.org/abs/2408.09834v3
• Date: Fri, 30 Aug 2024 13:54:36 GMT
• Title: Minor DPO reject penalty to increase training robustness
• Authors: Shiming Xie, Hong Chen, Fred Yu, Zeye Sun, Xiuyu Wu, Yingfan Hu,
• Abstract summary: Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. Recently, Direct Preference Optimization (DPO) has been proposed to solve the alignment problem with a simplified RL-free method. In this article, we analyze the working mechanism of $beta$ in DPO, disclose its syntax difference between RL algorithm and DPO, and understand the potential shortage brought by the DPO simplification.
• Score: 8.971332948872185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback (RLHF) algorithm to optimize the LLM policy to align with these preferences and not to draft too far from the original model. Recently, Direct Preference Optimization (DPO) has been proposed to solve the alignment problem with a simplified RL-free method. Using preference pairs of chosen and reject data, DPO models the relative log probability as implicit reward function and optimize LLM policy using a simple binary cross entropy objective directly. DPO is quite straight forward and easy to be understood. It perform efficiently and well in most cases. In this article, we analyze the working mechanism of $\beta$ in DPO, disclose its syntax difference between RL algorithm and DPO, and understand the potential shortage brought by the DPO simplification. With these insights, we propose MinorDPO, which is better aligned to the original RL algorithm, and increase the stability of preference optimization process.

Related papers

• Accelerated Preference Optimization for Large Language Model Alignment [60.22606527763201]
  Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO) formulates RLHF as a policy optimization problem without explicitly estimating the reward function. We propose a general Accelerated Preference Optimization (APO) framework, which unifies many existing preference optimization algorithms.
  arXiv  Detail & Related papers  (2024-10-08T18:51:01Z)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  We present a new offline alignment algorithm, $chi2$-Preference Optimization ($chi$PO) $chi$PO implements the principle of pessimism in the face of uncertainty via regularization. It is provably robust to overoptimization and achieves sample-complexity guarantees based on single-policy concentrability.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• Hybrid Preference Optimization: Augmenting Direct Preference Optimization with Auxiliary Objectives [0.5120567378386615]
  We propose a hybrid approach to aligning large language models (LLMs) With a simple augmentation to the implicit reward decomposition of DPO, we allow for tuning LLMs to maximize a set of arbitrary auxiliary rewards. The proposed method, Hybrid Preference Optimization (HPO), shows the ability to effectively generalize to both user preferences and auxiliary designer objectives.
  arXiv  Detail & Related papers  (2024-05-28T08:35:48Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
  We introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
  arXiv  Detail & Related papers  (2024-05-26T00:29:04Z)
• RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models [7.676477609461592]
  Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. DPO relies on contrastive responses generated from human annotator and alternative LLM, instead of the policy model. In this paper, we address both challenges by systematically combining sampling rejection (RS) and DPO. Our proposed method effectively fine-tunes LLMs with limited resource environments, leading to improved alignment with user intent.
  arXiv  Detail & Related papers  (2024-02-15T16:00:58Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• Preference as Reward, Maximum Preference Optimization with Importance Sampling [3.7040071165219595]
  We propose a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO) MPO achieves the best of both worlds by combining the objectives of RLHF and IPO while being an off-policy algorithm.
  arXiv  Detail & Related papers  (2023-12-27T06:34:54Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)

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.