{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/is-prompt-based-finetuning-always-better-than","title":"Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding","arxiv_id":"2307.07880","date":"2023-07-15","proceeding":null,"authors":["Bolei Ma","Ercong Nie","Helmut Schmid","Hinrich Schütze"],"abstract":"Multilingual pretrained language models (MPLMs) have demonstrated substantial performance improvements in zero-shot cross-lingual transfer across various natural language understanding tasks by finetuning MPLMs on task-specific labelled data of a source language (e.g. English) and evaluating on a wide range of target languages. Recent studies show that prompt-based finetuning surpasses regular finetuning in few-shot scenarios. However, the exploration of prompt-based learning in multilingual tasks remains limited. In this study, we propose the ProFiT pipeline to investigate the cross-lingual capabilities of Prompt-based Finetuning. We conduct comprehensive experiments on diverse cross-lingual language understanding tasks (sentiment classification, paraphrase identification, and natural language inference) and empirically analyze the variation trends of prompt-based finetuning performance in cross-lingual transfer across different few-shot and full-data settings. Our results reveal the effectiveness and versatility of prompt-based finetuning in cross-lingual language understanding. Our findings indicate that prompt-based finetuning outperforms vanilla finetuning in full-data scenarios and exhibits greater advantages in few-shot scenarios, with different performance patterns dependent on task types. Additionally, we analyze underlying factors such as language similarity and pretraining data size that impact the cross-lingual performance of prompt-based finetuning. Overall, our work provides valuable insights into the cross-lingual prowess of prompt-based finetuning.","url_abs":"https://arxiv.org/abs/2307.07880v1","url_pdf":"https://arxiv.org/pdf/2307.07880v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"is-prompt-based-finetuning-always-better-than","repo_url":"https://github.com/boleima/profit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"zero-shot-cross-lingual-transfer","task_name":"Zero-Shot Cross-Lingual Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.07880","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}