From Zero to RAGs. Balancing job-NER performance with Token Cost
Loading...
Author (Corporation)
Publication date
2026
Type of student thesis
Course of study
Collections
Type
04B - Conference paper
Editor (Corporation)
Supervisor
Parent work
Data Science and Security. Proceedings of IDSCS 2025, Volume 2
Special issue
DOI of the original publication
Link
Related research data
Series
Lecture Notes in Networks and Systems (LNNS)
Series number
1945
Volume
2
Issue / Number
Pages / Duration
25-37
Patent number
Publisher / Publishing institution
Springer
Place of publication / Event location
Bangalore
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
We investigate prompt-optimization strategies for domain-specific named entity recognition in job advertisements by balancing the extraction performance against the number of tokens. Using the SKILLSPAN corpus, we implement six pipelines combining three prompting methods, zero-shot, hard-coded few-shot, and dynamic RAG-based few-shot, with optional RAG-based semantic prefiltering. Each pipeline extracts skills and via GPT-4o-mini, measuring F1, precision, recall, and average tokens per advertisement. The results show that dynamic RAG-few-shot without prefiltering achieves the highest F1 (≈71% for knowledge, ≈60% for skills) and that prefiltering might reduce token usage by up to 70% while modestly lowering recall. Compared to zero-shot, few-shot prompting, especially with RAG retrieval, yields substantial recall gains of up to 28% at the cost of precision. Our findings demonstrate that RAG-augmented few-shot prompting offers an effective, token-efficient solution for specialized NER tasks.
Keywords
Subject (DDC)
Event
International Conference on Data Science for Computational Security (IDSCS 2025)
Exhibition start date
Exhibition end date
Conference start date
14.11.2025
Conference end date
15.11.2025
Date of the last check
ISBN
978-3-032-24074-3
978-3-032-24075-0
978-3-032-24075-0
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
peer-reviewed
Open access category
Closed
Citation
Moser, D., Dornberger, R., & Hanne, T. (2026). From Zero to RAGs. Balancing job-NER performance with Token Cost. In S. Shukla, H. Sayama, K. Tiwari, J. P. George, & J. V. Kureethara (Eds.), Data Science and Security. Proceedings of IDSCS 2025, Volume 2 (Vol. 2, pp. 25–37). Springer. https://doi.org/10.1007/978-3-032-24075-0_3