对齐知识图谱与语言模型以提升事实准确性
Aligning Knowledge Graphs and Language Models for Factual Accuracy
AI总结：
本文提出 ALIGNed-LLM，通过将知识图谱嵌入对齐到语言模型潜在空间来增强事实依据并减少幻觉，在多个问答基准和真实金融场景中均取得显著改进。
摘要：
GPT-4、Gemini 和 Claude 等大型语言模型已经变革了问答、对话生成、摘要等自然语言处理（NLP）任务；然而，它们容易产生幻觉仍然是主要挑战之一。在众多应对这一挑战的方法中，将知识图谱（Knowledge Graphs, KGs）集成到语言模型中已成为一种有前景的解决方案，因为它能为语言模型提供结构化、可靠、领域特定且最新的外部信息。本文提出 ALIGNed-LLM，这是一种简单而有效的方法，通过一种精简策略将知识图谱注入语言模型的潜在空间，从而提升语言模型的事实性，其灵感来自 LLaVA 中注入视觉和文本信息的方式。我们使用来自预训练知识图谱嵌入（Knowledge Graph Embedding, KGE）模型（如 TransE）的嵌入以及一个可训练的投影层来对齐实体和文本嵌入。这种对齐使语言模型能够区分相似实体，从而改善事实依据并减少幻觉。我们在三个流行的问答基准数据集上，结合不同规模的语言模型测试了该方法，结果显示有显著改进。此外，我们将该方法应用于欧洲一家大型中央银行的真实金融用例，该用例要求高准确性和高精度，结果表明大语言模型（LLM）的回答质量得到了显著提升。
英文摘要：
Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so forth; yet their susceptibility to hallucination stands as one of the major challenges. Among numerous approaches to overcome this challenge, integration of Knowledge Graphs (KGs) into language models has emerged as a promising solution as it provides structured, reliable, domain-specific, and up-to-date external information to the language models. In this paper, we introduce ALIGNed-LLM, a simple yet effective approach to improve language models' factuality via a lean strategy to infuse KGs into the latent space of language models inspired by LLaVA where visual and textual information is infused. We use embeddings from a pre-trained Knowledge Graph Embedding (KGE) model, such as TransE, and a trainable projection layer to align entity and text embeddings. This alignment enables the language model to distinguish between similar entities improving factual grounding and reducing hallucination. We tested our approach on three popular questions-answering benchmark datasets alongside language models of varying sizes, showing significant improvement. Furthermore, we applied our approach to a real-world financial use case from a large central bank in Europe, which demands high accuracy and precision, demonstrating a substantial improvement of the LLM answers.
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。
