Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Model

Domain:

natural language processing

Record type:

paper
Creator:
ParParYooYoo
Host:avatar
An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models. To further improve model adaptation to cross-lingual tasks, another trend is to further fine-tune the language models with either full fine-tuning or parameter-efficient tuning. However, the interaction between parameter-efficient fine-tuning (PEFT) and cross-lingual tasks in multilingual autoregressive models has yet to be studied. Specifically, we lack an understanding of the role of linguistic distributions in multilingual models in the effectiveness of token-based prompt tuning. To address this question, we conduct experiments comparing prompt tuning and fine-tuning on the decoder-based multilingual model, XGLM, with four cross-lingual tasks (XNLI, PAWS-X, POS, NER). According to our study, prompt tuning achieves on par or better performance over fine-tuning across all languages while updating at most 0.13\% of the model parameters. Moreover, we empirically show that prompt tuning is more effective in enhancing the performance of low-resource languages than fine-tuning. Our further analysis shows that the phenomenon is related to the tokenization scheme of the multilingual model.

Visit

arxiv.org

Tasks

transfer learning

Tags

Computation and Language

Similar

Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic ModelProjection-based Data Transfer versus Direct Multilingual Fine-tuning for Cross-lingual NER PerformanceComparative Analysis of Prefix-Tuning and Adapter-Based Fine-Tuning for Zero-Shot Cross-Lingual Generation on Low-ResourceComparative Analysis of Multilingual and English-Only Intermediate Fine-Tuning for Zero-Shot Cross-Lingual Transfer on XTREME-RFew-shot Prompt Learning vs. Fine-tuning for Cross-lingual NER in Low-Resource LanguagesPerformance comparison of hybrid batch training and multilingual fine-tuning on zero-shot cross-lingual retrieval for

Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to

Projection-based Data Transfer versus Direct Multilingual Fine-tuning for Cross-lingual NER Performance

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Comparative Analysis of Prefix-Tuning and Adapter-Based Fine-Tuning for Zero-Shot Cross-Lingual Generation on Low-Resource

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual

Comparative Analysis of Multilingual and English-Only Intermediate Fine-Tuning for Zero-Shot Cross-Lingual Transfer on XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Few-shot Prompt Learning vs. Fine-tuning for Cross-lingual NER in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Performance comparison of hybrid batch training and multilingual fine-tuning on zero-shot cross-lingual retrieval for

Information retrieval across different languages is an increasingly important challenge in natural l