Computational Cost Comparison of Sequential vs. Single Intermediate-Task Training for Large Language Models in Cross-Lingual

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: How does the computational cost (measured in GPU hours or inference latency) of sequential intermediate-task training compare to single intermediate-task training when scaling to larger language models (e.g., 10B+ parameters) for cross-lingual transfer?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.