AIPO: Improving Training Objective for Iterative Preference Optimization

• URL: http://arxiv.org/abs/2409.08845v1
• Date: Fri, 13 Sep 2024 14:03:49 GMT
• Title: AIPO: Improving Training Objective for Iterative Preference Optimization
• Authors: Yaojie Shen, Xinyao Wang, Yulei Niu, Ying Zhou, Lexin Tang, Libo Zhang, Fan Chen, Longyin Wen,
• Abstract summary: We study iterative preference optimization with synthetic data. We propose our training objective for iterative preference optimization, namely Agreement-aware Iterative Preference Optimization (AIPO)
• Score: 34.24211649396053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Preference Optimization (PO), is gaining popularity as an alternative choice of Proximal Policy Optimization (PPO) for aligning Large Language Models (LLMs). Recent research on aligning LLMs iteratively with synthetic or partially synthetic data shows promising results in scaling up PO training for both academic settings and proprietary trained models such as Llama3. Despite its success, our study shows that the length exploitation issue present in PO is even more severe in Iterative Preference Optimization (IPO) due to the iterative nature of the process. In this work, we study iterative preference optimization with synthetic data. We share the findings and analysis along the way of building the iterative preference optimization pipeline. More specifically, we discuss the length exploitation issue during iterative preference optimization and propose our training objective for iterative preference optimization, namely Agreement-aware Iterative Preference Optimization (AIPO). To demonstrate the effectiveness of our method, we conduct comprehensive experiments and achieve state-of-the-art performance on MT-Bench, AlpacaEval 2.0, and Arena-Hard. Our implementation and model checkpoints will be made available at https://github.com/bytedance/AIPO.

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)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Two Optimizers Are Better Than One: LLM Catalyst Empowers Gradient-Based Optimization for Prompt Tuning [69.95292905263393]
  We show that gradient-based optimization and large language models (MsLL) are complementary to each other, suggesting a collaborative optimization approach. Our code is released at https://www.guozix.com/guozix/LLM-catalyst.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Localized Zeroth-Order Prompt Optimization [54.964765668688806]
  We propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO) ZOPO incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency.
  arXiv  Detail & Related papers  (2024-03-05T14:18:15Z)
• Unleashing the Potential of Large Language Models as Prompt Optimizers: An Analogical Analysis with Gradient-based Model Optimizers [108.72225067368592]
  We propose a novel perspective to investigate the design of large language models (LLMs)-based prompts. We identify two pivotal factors in model parameter learning: update direction and update method. In particular, we borrow the theoretical framework and learning methods from gradient-based optimization to design improved strategies.
  arXiv  Detail & Related papers  (2024-02-27T15:05:32Z)
• 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)
• From Function to Distribution Modeling: A PAC-Generative Approach to Offline Optimization [30.689032197123755]
  This paper considers the problem of offline optimization, where the objective function is unknown except for a collection of offline" data examples. Instead of learning and then optimizing the unknown objective function, we take on a less intuitive but more direct view that optimization can be thought of as a process of sampling from a generative model.
  arXiv  Detail & Related papers  (2024-01-04T01:32:50Z)

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.