QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

Zhuo Chen, Rumen Dangovski, Charlotte Loh, Owen M Dugan, Di Luo, Marin Soljacic

Keywords: LLM, Language Model, PEFT, Finetuning, High Rank

TL;DR: We propose Quantum-informed Tensor Adaptation (QuanTA), a novel, easy-to-implement, high-rank fine-tuning method with no inference overhead for large-scale pre-trained language models.

Abstract: We propose **Quan**tum-informed **T**ensor **A**daptation (**QuanTA**), a novel, easy-to-implement, fine-tuning method with no inference overhead for large-scale pre-trained language models. By leveraging quantum-inspired methods derived from quantum circuit structures, QuanTA enables efficient *high-rank* fine-tuning, surpassing the limitations of Low-Rank Adaptation (LoRA)---low-rank approximation may fail for complicated downstream tasks. Our approach is theoretically supported by the universality theorem and the rank representation theorem to achieve efficient high-rank adaptations. Experiments demonstrate that QuanTA significantly enhances commonsense reasoning, arithmetic reasoning, and scalability compared to traditional methods. Furthermore, QuanTA shows superior performance with fewer trainable parameters compared to other approaches and can be designed to integrate with existing fine-tuning algorithms for further improvement, providing a scalable and efficient solution for fine-tuning large language models and advancing state-of-the-art in natural language processing.

Primary Area: Natural language processing

Submission Number: 17751