优化粤语口语的检索增强生成（RAG）：一项基于 LoRA 的系统综述
Optimizing Retrieval-Augmented Generation (RAG) for Colloquial Cantonese: A LoRA-Based Systematic Review
AI总结：
本综述探讨了基于LoRA的参数高效微调（PEFT）在优化粤语口语RAG系统中的应用，发现动态和集成LoRA能减少参数且保持质量，但低资源语言细节保留及大规模鲁棒性仍待解决。
摘要：
本综述考察了参数高效微调（PEFT）的最新进展，重点关注低秩适应（LoRA），以优化如 Qwen3、DeepSeek 和 Kimi 等检索增强生成（RAG）系统。由于标注数据有限和语言变异性，这些系统在理解和生成地道的粤语口语表达方面面临挑战。本综述评估了 LoRA 在 RAG 框架中的集成，对 PEFT 方法在检索和生成准确性方面进行了基准测试，识别了有限数据下的领域适应策略，并比较了旨在提高数据稀缺条件下语义保真度的微调技术。通过对采用多种 LoRA 变体、合成数据生成、用户反馈集成和自适应参数分配的最新研究进行系统分析，评估了它们对计算效率、检索精度、语言真实性和可扩展性的影响。研究结果表明，动态和集成 LoRA 适应显著减少了可训练参数，同时没有牺牲方言语境下的检索准确性和生成质量。然而，在完全保留细粒度语言细微差别方面仍存在局限性，特别是对于像粤语这样的低资源环境。实时用户反馈和特定领域数据的集成仍然不完善，限制了模型的适应性和个性化。虽然选择性参数冻结和非线性适应方法在效率和准确性之间提供了更好的权衡，但它们在大规模下的鲁棒性仍然是一个开放性挑战。本综述强调了 PEFT 增强的 RAG 系统在特定领域语言任务中的潜力，并呼吁未来工作针对方言真实性、动态适应和可扩展微调流水线展开研究。
英文摘要：
This review examines recent advances in Parameter-Efficient Fine-Tuning (PEFT), with a focus on Low-Rank Adaptation (LoRA), to optimize Retrieval-Augmented Generation (RAG) systems like Qwen3, DeepSeek, and Kimi. These systems face challenges in understanding and generating authentic Cantonese colloquial expressions due to limited annotated data and linguistic variability. The review evaluates the integration of LoRA within RAG frameworks, benchmarks PEFT methods for retrieval and generation accuracy, identify domain adaptation strategies under limited data, and compares fine-tuning techniques aimed at improving semantic fidelity under data-scarce conditions. A systematic analysis of recent studies employing diverse LoRA variants, synthetic data generation, user feedback integration, and adaptive parameter allocation was conducted to assess their impact on computational efficiency, retrieval precision, linguistic authenticity, and scalability. Findings reveal that dynamic and ensemble LoRA adaptations significantly reduce trainable parameters without sacrificing retrieval accuracy and generation quality in dialectal contexts. However, limitations remain in fully preserving fine-grained linguistic nuances, especially for low-resource settings like Cantonese. The integration of real-time user feedback and domain-specific data remains underdeveloped, limiting model adaptability and personalization. While selective parameter freezing and nonlinear adaptation methods offer better trade-offs between efficiency and accuracy, their robustness at scale remains an open challenge. This review highlights the promise of PEFT-enhanced RAG systems for domain-specific language tasks and calls for future work targeting dialectal authenticity, dynamic adaptation, and scalable fine-tuning pipelines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
