Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation

TL;DR

This paper introduces smaller, efficient paraphrasing models distilled from large language models that maintain high quality, diversity, and syntactic variation while significantly reducing inference time and computational costs.

Contribution

The study presents a sequence-level knowledge distillation approach to create compact paraphrasing models that match LLM quality with faster inference and enhanced diversity.

Findings

Distilled models achieve only 4% performance drop compared to LLMs.

Models generate diverse paraphrases with syntactic and lexical variation.

Inference speed is significantly increased, reducing costs.

Abstract

Over the past year, the field of Natural Language Generation (NLG) has experienced an exponential surge, largely due to the introduction of Large Language Models (LLMs). These models have exhibited the most effective performance in a range of domains within the Natural Language Processing and Generation domains. However, their application in domain-specific tasks, such as paraphrasing, presents significant challenges. The extensive number of parameters makes them difficult to operate on commercial hardware, and they require substantial time for inference, leading to high costs in a production setting. In this study, we tackle these obstacles by employing LLMs to develop three distinct models for the paraphrasing field, applying a method referred to as sequence-level knowledge distillation. These distilled models are capable of maintaining the quality of paraphrases generated by the LLM. They demonstrate faster inference times and the ability to generate diverse paraphrases of comparable quality. A notable characteristic of these models is their ability to exhibit syntactic diversity while also preserving lexical diversity, features previously uncommon due to existing data quality issues in datasets and not typically observed in neural-based approaches. Human evaluation of our models shows that there is only a 4% drop in performance compared to the LLM teacher model used in the distillation process, despite being 1000 times smaller. This research provides a significant contribution to the NLG field, offering a more efficient and cost-effective solution for paraphrasing tasks.