使用大型语言模型进行职业分类的基于分类法引导推理的多阶段框架
A Multi-Stage Framework with Taxonomy-Guided Reasoning for Occupation Classification Using Large Language Models
AI总结：
本研究提出一个包含推理、检索和重排序的多阶段框架，通过集成分类法引导的推理示例，显著提升了LLMs的职业分类性能，为GPT-4o等前沿模型提供了低成本且可扩展的替代方案。
摘要：
将职位数据自动标注为分类法中的标准化职业（即职业分类），对劳动力市场分析至关重要。然而，该任务常受限于数据稀缺和人工标注的挑战。尽管大型语言模型（LLMs）凭借其广泛的世界知识和上下文学习能力展现出潜力，但其有效性取决于对职业分类法的掌握程度，而这方面仍不明确。在本研究中，我们评估了LLMs从分类法中生成精确分类实体的能力，揭示了其局限性，尤其是在较小模型上。为应对这些挑战，我们提出了一个包含推理、检索和重排序阶段的多阶段框架，该框架集成了分类法引导的推理示例，通过将输出与分类知识对齐来提升性能。在大规模数据集上的评估表明，我们的框架不仅增强了职业和技能分类任务，还为GPT-4o等前沿模型提供了高性价比的替代方案，在保持强劲性能的同时显著降低了计算成本。这使其成为跨LLMs的职业分类及相关任务的实用且可扩展的解决方案。
英文摘要：
Automatically annotating job data with standardized occupations from taxonomies, known as occupation classification, is crucial for labor market analysis. However, this task is often hindered by data scarcity and the challenges of manual annotations. While large language models (LLMs) hold promise due to their extensive world knowledge and in-context learning capabilities, their effectiveness depends on their knowledge of occupational taxonomies, which remains unclear. In this study, we assess the ability of LLMs to generate precise taxonomic entities from taxonomy, highlighting their limitations, especially for smaller models. To address these challenges, we propose a multi-stage framework consisting of inference, retrieval, and reranking stages, which integrates taxonomy-guided reasoning examples to enhance performance by aligning outputs with taxonomic knowledge. Evaluations on a large-scale dataset show that our framework not only enhances occupation and skill classification tasks, but also provides a cost-effective alternative to frontier models like GPT-4o, significantly reducing computational costs while maintaining strong performance. This makes it a practical and scalable solution for occupation classification and related tasks across LLMs.
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。
