Reproduce “DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job Recommendation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiaoshan Yu, Chuan Qin, Qi Zhang, Chen Zhu, Haiping Ma, Xingyi Zhang, Hengshu Zhu
DISCO models job recommendations as skill diagnosis, representing candidate proficiency and job requirements across skill levels to predict recorded interactions. Its profiles expose the skill dimensions behind a recommendation, while a matched-pair case study illustrates rather than validates them. On the Technology benchmark, DISCO exceeds SHPJF on HR@5 and NDCG@5, but these ranking results do not establish hiring outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.