Comparative Analysis of Teacher-Student Learning and Few-Shot Prompting for Cross-Lingual NER on XTREME Benchmarks

This paper evaluates Few-Shot Prompting with Large Language Models for Named Entity Recognition (NER). Traditional NER systems rely on extensive labeled datasets, which are costly and time-consuming to obtain. Few-Shot Prompting or in-context learning enables models to recognize entities with minimal examples. We assess state-of-the-art models like GPT-4 in NER tasks, comparing their few-shot performance to fully supervised benchmarks. Results show that while there is a performance gap, large models excel in adapting to new entity types and domains with very limited data. We also explore the e

Research goal: How does the performance of teacher-student learning methods for cross-lingual NER compare to few-shot prompting in large language models (LLMs) on XTREME-NER benchmarks, measured by F1-score per entity type?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.