Domain Adaptation Effects on Zero-Shot Cross-Lingual Transfer in XTREME-R

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: To what extent does domain adaptation of intermediate-task datasets (e.g., switching from general NLP tasks to biomedical or legal tasks) impact zero-shot cross-lingual transfer performance on XTREME-R, measured by F1 score changes across different language families?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.