Published July 17, 2026 | Version v1

Comparative Analysis of Multilingual and English-Only Intermediate NLI Training for Zero-Shot XTREME Performance

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: How does intermediate-task training on multilingual NLI datasets compare to English-only NLI tasks for zero-shot performance on the XTREME benchmark measured by mF1 scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.9/10.

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: 8.9/10.

Files

paper.pdf

Files (79.9 kB)

Name Size Download all
md5:f5e09708b9e0059fc68cc61d75c784dd
79.9 kB Preview Download