Quantum-Inspired Fine-Tuning for Few-Shot AIGC Detection via Phase-Structured Reparameterization

2026-03-01

AI Summary

This work addresses the challenge of efficiently and accurately detecting AI-generated content (AIGC) in few-shot scenarios, where existing methods often struggle. To this end, we propose Q-LoRA and H-LoRA—two parameter-efficient fine-tuning approaches that, for the first time, integrate the phase structure from quantum neural networks and the Hilbert transform into the low-rank adaptation (LoRA) framework. These methods inject structured inductive bias through phase-aware representations and norm constraints. Experimental results demonstrate that both Q-LoRA and H-LoRA consistently outperform standard LoRA by over 5% in accuracy on few-shot AIGC detection tasks. Notably, the fully classical H-LoRA achieves this performance gain while significantly reducing computational overhead, offering a practical balance between efficacy and efficiency.

Technology Category

• Machine Learning: Quantum Machine Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent studies show that quantum neural networks (QNNs) generalize well in few-shot regimes. To extend this advantage to large-scale tasks, we propose Q-LoRA, a quantum-enhanced fine-tuning scheme that integrates lightweight QNNs into the low-rank adaptation (LoRA) adapter. Applied to AI-generated content (AIGC) detection, Q-LoRA consistently outperforms standard LoRA under few-shot settings. We analyze the source of this improvement and identify two possible structural inductive biases from QNNs: (i) phase-aware representations, which encode richer information across orthogonal amplitude-phase components, and (ii) norm-constrained transformations, which stabilize optimization via inherent orthogonality. However, Q-LoRA incurs non-trivial overhead due to quantum simulation. Motivated by our analysis, we further introduce H-LoRA, a fully classical variant that applies the Hilbert transform within the LoRA adapter to retain similar phase structure and constraints. Experiments on few-shot AIGC detection show that both Q-LoRA and H-LoRA outperform standard LoRA by over 5% accuracy, with H-LoRA achieving comparable accuracy at significantly lower cost in this task.

Problem

• few-shot learning
• AIGC detection
• quantum-inspired methods
• low-rank adaptation
• phase-structured representation

Innovation

• quantum-inspired fine-tuning
• phase-structured reparameterization
• LoRA
• few-shot AIGC detection
• Hilbert transform