用AI扩展分类体系，避免生成错误内容。
ReLTEx: Reliable LLM-based Taxonomy Expansion
- 先让大模型生成候选概念，再通过结构校验筛选
- 在基准测试中比其他方法减少40%以上错误扩展
- 适合需要高质量分类体系的智能系统开发
大型语言模型在生成语义相关概念与关系方面表现出强大能力，是分类体系扩充的有力工具。然而，直接依赖模型生成的结果常导致噪声、冗余或层级不一致的问题，影响其可靠性。本文提出ReLTEx框架，结合大模型驱动的候选生成、结构感知验证和递归扩展控制，有效降低幻觉，提升生成分类体系的一致性与质量。在掩码分类体系扩展设置下，使用基准分类体系评估多种验证策略。实验结果表明，无论是改进后的评估指标还是人工评估，ReLTEx均能生成更可靠、语义连贯的分类体系扩展。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for taxonomy enrichment. However, directly relying on LLM-generated expansions often leads to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion. In this paper, we present ReLTEx, a framework for reliable LLM-based taxonomy expansion. ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to improve the consistency and quality of generated taxonomies by reducing hallucinations. We evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting and compare multiple validation strategies. Experimental results, supported by both adapted evaluation metrics and human evaluation, demonstrate that ReLTEx produces more reliable and semantically coherent taxonomy expansions.
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。