AI Intern

The candidate will work in high visibility projects as a Data Scientist, bringing Data Science and NLP expertise to projects. The candidate will work in the RD Data Science team and collaborate with Product managers, domain experts, and Knowledge representation experts to build high value outcomes from Elsevier content. The candidate will have an opportunity to impact virtually all Elsevier applications related to Research and Operations.

This project will focus on "The Effectiveness of Different Knowledge Distillation Approaches on the Performance of Ranking Models". We will utilize existing manually labeled datasets alongside LLM-generated labels, analyzing the correlation between human and LLM assessments across different relevance labeling setups (pointwise, pairwise, listwise). Then, we will leverage LLMs to create three distinct datasets (pointwise, pairwise, listwise) and subsequently train and evaluate re-rankers using these datasets in a sequential fashion.