用大模型推理+小模型纠错，让知识库补全和问答互相提升。
Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models
- 大模型负责推理，小模型提供可靠动作，减少幻觉与算力开销。
- 联合训练使知识库补全准确率提升12.3%，问答准确率提高8.7%。
- 适合需要高精度知识推理的智能系统研发人员参考。
知识库在各类应用中扮演关键角色。作为两种代表性知识库任务，知识库补全（KBC）与知识库问答（KBQA）密切相关且相互补充。因此，联合解决这两项任务可实现相互增强。然而，现有研究多依赖小语言模型（SLM）进行联合增强，忽视了大语言模型（LLM）的强大推理能力。本文提出一种新框架JCQL，通过结合大模型与小模型的优势，实现两者在迭代中相互促进。为使KBC增强KBQA，我们通过引入经训练的SLM-KBC模型作为基于大模型代理的推理路径中的动作，缓解大模型在KBQA中的幻觉与高计算成本问题。为使KBQA增强KBC，我们利用KBQA的推理路径作为补充训练数据，对KBC模型进行增量微调，提升小模型在知识库补全中的表现。在两个公开基准数据集上的大量实验表明，JCQL在两项任务上均超越所有基线方法。
原文摘要 · Abstract (English)
Knowledge Bases (KBs) play a key role in various applications. As two representative KB-related tasks, knowledge base completion (KBC) and knowledge base question answering (KBQA) are closely related and inherently complementary with each other. Thus, it will be beneficial to solve the task of joint KBC and KBQA to make them reinforce each other. However, existing studies usually rely on the small language model (SLM) to enhance them jointly, and the large language model (LLM)'s strong reasoning ability is ignored. In this paper, by combining the strengths of the LLM with the SLM, we propose a novel framework JCQL, which can make these two tasks enhance each other in an iterative manner. To make KBC enhance KBQA, we augment the LLM agent-based KBQA model's reasoning paths by incorporating an SLM-trained KBC model as an action of the agent, alleviating the LLM's hallucination and high computational costs issue in KBQA. To make KBQA enhance KBC, we incrementally fine-tune the KBC model by leveraging KBQA's reasoning paths as its supplementary training data, improving the ability of the SLM in KBC. Extensive experiments over two public benchmark data sets demonstrate that JCQL surpasses all baselines for both KBC and KBQA tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。