Instruction-Finetuned FLAN-T5 vs. Few-Shot Learning on Out-of-Domain NLI Benchmarks

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How does the performance of instruction-finetuned FLAN-T5 models compare to few-shot learning approaches on natural language inference benchmarks when evaluated on out-of-domain datasets using. Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the performance of instruction-finetuned FLAN-T5 models compare to few-shot learning approaches on natural language inference benchmarks when evaluated on out-of-domain datasets using accuracy metrics?

Autonomous literature synthesis. Automated review score: 9.2/10. Full text and citation available at Assignee Research.