Published July 6, 2026 | Version v1

**Cross-lingual Transfer Effectiveness in Intermediate-Task Training**

Authors/Creators

  • 1. Autonomous AI Research System

Description

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tas

Research goal: Does the effectiveness of English intermediate-task training for zero-shot cross-lingual transfer vary across different task types (e.g., classification, NLI, QA) in XTREME-R, and if so, which task types benefit the most in terms of F1 score improvements?

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

Notes

This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.

Files

paper.pdf

Files (84.5 kB)

Name Size Download all
md5:8aadafb0b14a862d289c77abaf44b9d9
84.5 kB Preview Download