QuLoC：光子量子辅助的低秩大语言模型压缩

中文摘要 AI 辅助

随着大语言模型（LLM）规模的不断增大，压缩对于高效部署变得越来越重要。基于奇异值分解（SVD）的低秩压缩方法能够减少参数数量，但可能会降低下游任务的性能。为了提升压缩后的模型性能，我们提出了QuLoC，一种光子量子辅助的大语言模型压缩算法，该算法利用量子电路的输出在训练过程中对保留的低秩分量进行门控。模型性能通过局部功能重构以及随后的端到端知识蒸馏得以恢复。训练完成后，门控系数被吸收进低秩因子中，使得压缩后的模型能够在经典硬件上运行，而无需在推理阶段执行量子电路。在Qwen3.5-4B上的实验表明，QuLoC在多个下游任务上的平均准确率相较于最先进的基线方法取得了9.73%的相对提升，证明了其有效性。我们进一步在LLaMA-7B上以不同的参数压缩比例评估了QuLoC。它在不同压缩设置下均持续取得比最先进基线更高的平均下游准确率，支持了其适用于更大模型的可扩展性。值得注意的是，使用光子量子硬件进行的实验在相对于模拟仅有微小准确率损失的情况下保留了这些优势，表明其对硬件噪声具有鲁棒性。这些结果激励了进一步探索光子量子辅助压缩在更大模型和更复杂的智能体任务中的应用。

英文摘要

As LLMs grow in size, compression becomes increasingly important for efficient deployment. SVD-based low-rank compression reduces parameter counts but can degrade downstream performance. To improve performance after compression, we introduce QuLoC, a photonic quantum-assisted LLM compression algorithm that uses quantum circuit outputs to gate the retained low-rank components during training. Model performance is recovered through local functional reconstruction followed by end-to-end knowledge distillation. After training, the gating coefficients are absorbed into the low-rank factors, allowing the compressed model to run on classical hardware without executing quantum circuits during inference. Experiments on Qwen3.5-4B show that QuLoC achieves a 9.73\% relative improvement in average accuracy over state-of-the-art baselines across multiple downstream tasks, demonstrating its effectiveness. We further evaluate QuLoC on LLaMA-7B at different parameter compression ratios. It achieves comparable or higher average downstream accuracy than state-of-the-art baselines, supporting its applicability to a larger model across different compression settings. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks.

发表机构

• TuringQ Co., Ltd.（图灵量子有限公司）
• Atomology Co., Ltd.（阿托莫罗科技有限公司）
• Hefei National Laboratory（合肥国家实验室）

机构由 AI 辅助整理，请以论文原文为准。