Two-Stage Recruitment Text Labeling via Lexicon-Guided Routing and Retrieval-Augmented Large Language Models
Journal of Visualized Experiments · 2026
DOI: 10.3791/70153 ↗At a glance
Video/Audio in Journal of Visualized Experiments, 2026. Written by Hushuang Shen and 1 co-authors. Institution: School of Petroleum, China University of Petroleum-Beijing at Karamay Campus. Major MEDLINE topics: Natural Language Processing, Information Storage and Retrieval. 28 references.
Abstract (original language)
Recruitment texts are heterogeneous, and domain terminology evolves over time, making large-scale labeling difficult with limited manual annotation capacity. This protocol provides a reproducible two-stage workflow for classifying Chinese recruitment texts into Artificial Intelligence, Environmental Protection, or Other. Stage one performs lexicon-guided triage using two curated domain keyword lists. Postings that match only one domain lexicon are directly labeled. Postings that match neither lexicon are labeled as Other, while dual-match postings are routed to stage two. Stage two applies retrieval-augmented large language model inference. A knowledge base compiled from 12 authoritative domain documents is converted to text, split into about 1,000-character chunks with 20-character overlap, embedded using all-MiniLM-L6-v2, and indexed in LanceDB. For each uncertain posting, cosine-similarity k-nearest-neighbor retrieval returns candidate chunks filtered by a minimum similarity threshold (τ), and up to four chunks are injected into a fixed prompt template that defines label boundaries and constrains the output to a single label. A benchmark set of 3,000 postings is manually verified, with 1,000 postings per class, and achieves an inter-annotator agreement of 95.0 % and a Cohen's kappa (κ) of about 0.93. Evaluation compares multiple open-source large language models across a prompt-only setting and a retrieval-augmented setting using Qwen2.5-7B-Instruct. The retrieval-augmented configuration achieves 98.47 %accuracy and supports corpus-scale labeling of about 6.93 million postings for downstream descriptive aggregation.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- School of Petroleum, China University of Petroleum-Beijing at Karamay Campus.
- School of Business Administration, South China University of Technology; bmwangyuan@mail.scut.edu.cn.
Cite
APA
Shen, H., & Wang, Y. (2026). Two-Stage Recruitment Text Labeling via Lexicon-Guided Routing and Retrieval-Augmented Large Language Models. Journal of Visualized Experiments. https://doi.org/10.3791/70153
Vancouver
Shen H, Wang Y. Two-Stage Recruitment Text Labeling via Lexicon-Guided Routing and Retrieval-Augmented Large Language Models. Journal of Visualized Experiments. 2026. doi:10.3791/70153
BibTeX
@article{Shen2026,
author = {Shen, Hushuang and Wang, Yuan},
title = {Two-Stage Recruitment Text Labeling via Lexicon-Guided Routing and Retrieval-Augmented Large Language Models},
journal = {Journal of Visualized Experiments},
year = {2026},
doi = {10.3791/70153}
}
EUVIMED