# A Multi-Stage Framework with Taxonomy-Guided Reasoning for Occupation Classification Using Large Language Models

arXiv: https://arxiv.org/abs/2503.12989 · HTML: https://mlsanity.com/paper/2503.12989/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 9 of 9)

- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Extreme Multi-Label Skill Extraction Training using Large Language Models](https://mlsanity.com/paper/2307.10778/) (2023)
- [Design of Negative Sampling Strategies for Distantly Supervised Skill Extraction](https://mlsanity.com/paper/2209.05987/) (2022)
- [Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers](https://mlsanity.com/paper/2307.03539/) (2023)
- [Automatic Question-Answer Generation for Long-Tail Knowledge](https://mlsanity.com/paper/2403.01382/) (2024)
- [LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models](https://mlsanity.com/paper/2309.09708/) (2023)
- [In-Context Learning for Extreme Multi-Label Classification](https://mlsanity.com/paper/2401.12178/) (2024)

## Built on by (most cited first, 2 of 2)

- [Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn](https://mlsanity.com/paper/2607.24783/) (2026)
- [From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework](https://mlsanity.com/paper/2609.35806/) (2026)

## Abstract (arXiv)

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.