Scaling Intermediate-Task Data Size and Cross-Lingual Transfer Accuracy in XTREME-R Evaluations

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 scaling intermediate-task training data size on the accuracy of cross-lingual transfer in language models evaluated on XTREME-R metrics?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.