Hybrid Quantum Transformer for Language Generation
This work demonstrates the feasibility of integrating quantum computing into large-scale generative language models, addressing a gap in applying quantum methods to complex NLP tasks.
The authors tackled the problem of applying quantum computing to large-scale natural language generation by developing HyQuT, a hybrid quantum-classical Transformer model, which achieved comparable performance to classical models while replacing 10% of parameters with quantum components using only 10 qubits.
Although quantum computing has been increasingly applied to replace classical computation, most existing quantum or hybrid models remain confined to simple tasks, with no successful application to large-scale natural language generation to date. In this work, we present the first hybrid quantum-classical large language model (LLM) for natural language generation, HyQuT, capable of performing coherent and context-aware dialogue. The proposed architecture integrates variational quantum circuits (VQCs) into the Transformer framework at both 8M and 150M parameter scales. Experimental results show that a minimal number of qubits (10 qubits with 80 quantum gates) can replace about 10% of the classical parameters in the 150M-parameter model, while achieving comparable convergence stability and generation quality. This study provides an early demonstration of the feasibility of integrating quantum computing to large-scale generative language models.