Weak-to-Strong Extrapolation Expedites Alignment

• URL: http://arxiv.org/abs/2404.16792v2
• Date: Wed, 22 May 2024 19:33:30 GMT
• Title: Weak-to-Strong Extrapolation Expedites Alignment
• Authors: Chujie Zheng, Ziqi Wang, Heng Ji, Minlie Huang, Nanyun Peng,
• Abstract summary: We propose a method called ExPO to boost models' alignment with human preference. We demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models. We shed light on the essence of ExPO amplifying the reward signal learned during alignment training.
• Score: 135.12769233630362
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The open-source community is experiencing a surge in the release of large language models (LLMs) that are trained to follow instructions and align with human preference. However, further training to improve them still requires expensive computational resources and data annotations. Is it possible to bypass additional training and cost-effectively acquire better-aligned models? Inspired by the literature on model interpolation, we propose a simple method called ExPO to boost LLMs' alignment with human preference. Utilizing a model that has undergone alignment training (e.g., via DPO or RLHF) and its initial SFT checkpoint, ExPO directly obtains a better-aligned model by extrapolating from the weights of the initial and the aligned models, which implicitly optimizes the alignment objective via first-order approximation. Through experiments with twelve open-source LLMs on HuggingFace, we demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models, as evaluated on the mainstream LLM benchmarks AlpacaEval 2.0 and MT-Bench. Moreover, ExPO exhibits remarkable scalability across various model sizes (from 1.8B to 70B) and capabilities. Through controlled experiments and further empirical analyses, we shed light on the essence of ExPO amplifying the reward signal learned during alignment training. Our work demonstrates the efficacy of model extrapolation in expediting the alignment of LLMs with human preference, suggesting a promising direction for future research.

Related papers

• Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning [5.487210426671288]
  In this work, we demonstrate that the reasoning abilities of small-scale LMs can be enhanced through self-training. We also show that the conventional self-training can be further augmented by a preference learning algorithm called Direct Preference Optimization.
  arXiv  Detail & Related papers  (2024-07-25T17:59:16Z)
• Bootstrapping Language Models with DPO Implicit Rewards [45.68366127605774]
  Direct preference optimization (DPO) has greatly simplified the process from past work in reinforcement learning from human feedback. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach, named self-alignment with DPO ImpliCit rEwards (DICE), shows great improvements in alignment and achieves superior performance.
  arXiv  Detail & Related papers  (2024-06-14T06:57:18Z)
• Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
  Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback to improve model alignment. We propose a method to enhance LLM alignment through fine-grained token-level supervision.
  arXiv  Detail & Related papers  (2024-06-04T20:21:45Z)
• Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF [82.7679132059169]
  Reinforcement learning from human feedback has emerged as a central tool for language model alignment. We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO) XPO enjoys the strongest known provable guarantees and promising empirical performance.
  arXiv  Detail & Related papers  (2024-05-31T17:39:06Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model [3.300814846990438]
  Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. As they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that are not aligned with human values. This paper studies two main approaches to LLM alignment: Reinforcement Learning with Human Feedback (RLHF) and contrastive learning-based methods like Direct Preference Optimization (DPO) By analyzing the stability and robustness of RLHF and DPO, we propose MPO, a novel method that mitigates the weaknesses of both approaches.
  arXiv  Detail & Related papers  (2024-03-28T14:15:10Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• 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.