English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Numerous HR applications are centered around resumes and job descriptions.While they can benefit from advancements in NLP, particularly large languagemodels, their real-world adoption faces challenges due to absence ofcomprehensive benchmarks for various HR tasks, and lack of smaller models withcompetitive capabilities. In this paper, we aim to bridge this gap byintroducing the Resume-Job Description Benchmark (RJDB). We meticulously craftthis benchmark to cater to a wide array of HR tasks, including matching andexplaining resumes to job descriptions, extracting skills and experiences fromresumes, and editing resumes. To create this benchmark, we propose to distilldomain-specific knowledge from a large language model (LLM). We rely on acurated skill-occupation graph to ensure diversity and provide context for LLMsgeneration. Our benchmark includes over 50 thousand triples of jobdescriptions, matched resumes and unmatched resumes. Using RJDB, we trainmultiple smaller student models. Our experiments reveal that the student modelsachieve near/better performance than the teacher model (GPT-4), affirming theeffectiveness of the benchmark. Additionally, we explore the utility of RJDB onout-of-distribution data for skill extraction and resume-job descriptionmatching, in zero-shot and weak supervision manner. We release our datasets andcode to foster further research and industry applications.

Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks