Domain Similarity and Zero-Shot Cross-Lingual Transfer in XTREME-R with Hybrid Batch Training

Transfer learning from large language models (LLMs) has emerged as a powerful technique to enable knowledge-based fine-tuning for a number of tasks, adaptation of models for different domains and even languages. However, it remains an open question, if and when transfer learning will work, i.e. leading to positive or negative transfer. In this paper, we analyze the knowledge transfer across three natural language processing (NLP) tasks - text classification, sentimental analysis, and sentence similarity, using three LLMs - BERT, RoBERTa, and XLNet - and analyzing their performance, by fine-tun

Research goal: What is the impact of intermediate-task domain similarity (e.g., NLI vs. NER) on zero-shot cross-lingual transfer accuracy in XTREME-R when using hybrid batch training versus English-only fine-tuning?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.