让大模型推理时动态构建知识图谱，提升回答准确性。
Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
- 推理时动态构建知识图谱，融合模型内知识与外部检索。
- 在三个事实问答数据集上准确率显著优于基线方法。
- 结构化知识更易解释，适合需高可信度的场景。
大型语言模型（LLMs）常因参数记忆有限而产生事实不一致的回答。检索增强生成（RAG）虽能缓解此问题，但通常将知识视为非结构化文本，降低检索精度，阻碍组合推理，并放大无关信息对事实一致性的影响。为此，我们提出一种新框架：在推理过程中动态构建并扩展知识图谱（KG），融合模型内部提取的知识与外部来源检索到的信息。方法首先通过提示词从问题中提取初始知识图谱，再利用模型内部知识进行迭代扩展；随后通过外部检索选择性地精炼知识图谱，提升事实覆盖范围并修正错误。我们在三个不同的事实问答基准上评估该方法，结果表明其在事实准确性上持续优于基线。研究发现，推理时构建知识图谱是提升大模型事实性的一种结构化、可解释且可扩展的有前景方向。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) paradigms mitigate this issue by incorporating external knowledge at inference time. However, such methods typically handle knowledge as unstructured text, which reduces retrieval accuracy, hinders compositional reasoning, and amplifies the influence of irrelevant information on the factual consistency of LLM outputs. To overcome these limitations, we propose a novel framework that dynamically constructs and expands knowledge graphs (KGs) during inference, integrating both internal knowledge extracted from LLMs and external knowledge retrieved from external sources. Our method begins by extracting a seed KG from the question via prompting, followed by iterative expansion using the LLM's internal knowledge. The KG is then selectively refined through external retrieval, enhancing factual coverage and correcting inaccuracies. We evaluate our approach on three diverse Factual QA benchmarks, demonstrating consistent gains in factual accuracy over baselines. Our findings reveal that inference-time KG construction is a promising direction for enhancing LLM factuality in a structured, interpretable, and scalable manner.
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。