Published July 1, 2026 | Version v1

Zero-Shot Cross-Lingual Transfer in XTREME: Intermediate-Task Training Effects on Non-European Languages

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 English intermediate-task training improve zero-shot cross-lingual transfer on non-European languages in the XTREME benchmark compared to European languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.1/10.

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: 9.1/10.

Files

paper.pdf

Files (78.6 kB)

Name Size Download all
md5:be688b9969e3ee4a8ff6357c563108ef
78.6 kB Preview Download