How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

• URL: http://arxiv.org/abs/2410.10093v1
• Date: Mon, 14 Oct 2024 02:21:29 GMT
• Title: How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
• Authors: Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant G Honavar,
• Abstract summary: This paper introduces a novel generalized self-imitation learning ($textbfGSIL$) framework. It effectively and efficiently aligns large language models with offline demonstration data. $textbfGSIL$ consistently and significantly outperforms baselines in many challenging benchmarks.
• Score: 17.956310574300765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a novel generalized self-imitation learning ($\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data. We develop $\textbf{GSIL}$ by deriving a surrogate objective of imitation learning with density ratio estimates, facilitating the use of self-generated data and optimizing the imitation learning objective with simple classification losses. $\textbf{GSIL}$ eliminates the need for complex adversarial training in standard imitation learning, achieving lightweight and efficient fine-tuning for large language models. In addition, $\textbf{GSIL}$ encompasses a family of offline losses parameterized by a general class of convex functions for density ratio estimation and enables a unified view for alignment with demonstration data. Extensive experiments show that $\textbf{GSIL}$ consistently and significantly outperforms baselines in many challenging benchmarks, such as coding (HuamnEval), mathematical reasoning (GSM8K) and instruction-following benchmark (MT-Bench).

Related papers

• Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation [2.0411082897313984]
  This study introduces a novel methodology that integrates human annotators and Large Language Models. The proposed framework integrates human annotation with the output of LLMs, depending on the model uncertainty levels. The empirical results show a substantial decrease in the costs associated with data annotation while either maintaining or improving model accuracy.
  arXiv  Detail & Related papers  (2024-06-17T21:45:48Z)
• Self-training Large Language Models through Knowledge Detection [26.831873737733737]
  Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects.
  arXiv  Detail & Related papers  (2024-06-17T07:25:09Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation [105.23631749213729]
  We propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts. We show that our method can converge faster and perform better than CNN-based models in low-data regimes.
  arXiv  Detail & Related papers  (2024-05-22T06:48:43Z)
• $\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning [7.04736023670375]
  We introduce Gradient-based and Task-Agnostic machine Unlearning ($nabla tau$) $nabla tau$ applies adaptive gradient ascent to the data to be forgotten while using standard gradient descent for the remaining data. We evaluate our framework's effectiveness using a set of well-established Membership Inference Attack metrics.
  arXiv  Detail & Related papers  (2024-03-21T12:11:26Z)
• PanGu-$\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation [97.78045712375047]
  We present a new efficient model architecture for large language models (LLMs) We show that PanGu-$pi$-7B can achieve a comparable performance to that of benchmarks with about 10% inference speed-up. In addition, we have deployed PanGu-$pi$-7B in the high-value domains of finance and law, developing an LLM named YunShan for practical application.
  arXiv  Detail & Related papers  (2023-12-27T11:49:24Z)
• One-Shot Open Affordance Learning with Foundation Models [54.15857111929812]
  We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category. We propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data.
  arXiv  Detail & Related papers  (2023-11-29T16:23:06Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
  We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
  arXiv  Detail & Related papers  (2021-01-02T01:15:57Z)

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.