摘要
在知识检索的前沿领域,尤其是在大语言模型的应用场景下,研究焦点集中在用纯向量检索技术来高效捕获相关信息,继而将这些信息送入大语言模型进行综合提炼和概括。然而,这种方法的局限性在于,仅依赖向量表示可能无法全面把握检索的复杂性,且缺乏有效的排序机制,常使得无关信息冗余,进而削弱了最终答案与用户实际需求的匹配度。为解决这一难题,提出了基于混合检索增强的双塔模型。此模型创新性地融合了多路径召回策略,通过多样化的召回机制互补,确保检索结果既全面又高度相关。模型架构上,采用双层结构,结合了双向循环神经网络与文本卷积神经网络,使得模型可以对检索结果进行多层次的排序优化,极大地提高了结果的相关性和顶部结果的精确度。更进一步,将经过高效排序的高质量信息与原始查询一同送入大语言模型,充分利用其深层次的分析功能,生成更为精准和可信的答案。实验结果表明,提出的方法有效提升了检索的准确性和系统的整体性能,极大地增强了大语言模型在实际应用中的准确度和实用性。
In the vanguard of knowledge retrieval,particularly in scenarios involving large language models(LLMs),research emphasis has shifted toward employing pure vector retrieval techniques for efficient capture of pertinent information.This information is then fed into large language models for comprehensive distillation and summarization.However,the limitations of this approach lie in its potential inability to fully encompass the intricacies of retrieval through vector representations alone,coupling with an absence of effective ranking mechanisms.This often leads to an overabundance of irrelevant information,thereby diluting the alignment between the final response and the user’s actual needs.To address this conundrum,this paper introduces a hybrid retrieval-augmented dual-tower model.This model innovatively integrates a multi-path recall strategy,ensuring that the retrieval results are both comprehensive and highly relevant through complementary recall mechanisms.Architecturally,it adopts a dual-layer structure,combining bidirectional recurrent neural networks with text convolutional neural networks.This allows the model to perform multi-level ranking optimization on retrieval results,significantly enhancing the relevance and the precision of top-ranking outcomes.Moreover,the high-quality information,efficiently ranked,is integrated with the original query and fed into a large language model.This exploits the model’s deep analytical capabilities to generate more accurate and credible responses.Experimental findings affirm that the proposed method effectively improves retrieval accuracy and system performance overall,markedly enhancing the precision and practicality of large language models in real-world applications.
作者
郜洪奎
马瑞祥
包骐豪
夏少杰
瞿崇晓
GAO Hongkui;MA Ruixiang;BAO Qihao;XIA Shaojie;QU Chongxiao(The 52nd Research Institute of China Electronics Technology Group Corporation,Hangzhou 311100,China)
出处
《计算机科学》
北大核心
2025年第6期324-329,共6页
Computer Science
关键词
知识搜索
大语言模型
向量检索技术
混合检索增强的双塔模型
多路径召回策略
Knowledge search
Large language models
Vector retrieval technology
Hybrid retrieval-augmented dual-tower model
Multi-path recall strategy
