{"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/revisiting-automated-prompting-are-we","title":"Revisiting Automated Prompting: Are We Actually Doing Better?","arxiv_id":"2304.03609","date":"2023-04-07","proceeding":null,"authors":["Yulin Zhou","Yiren Zhao","Ilia Shumailov","Robert Mullins","Yarin Gal"],"abstract":"Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate human-led prompting followed, with some progress achieved. In particular, subsequent work demonstrates automation can outperform fine-tuning in certain K-shot learning scenarios. In this paper, we revisit techniques for automated prompting on six different downstream tasks and a larger range of K-shot learning settings. We find that automated prompting does not consistently outperform simple manual prompts. Our work suggests that, in addition to fine-tuning, manual prompts should be used as a baseline in this line of research.","url_abs":"https://arxiv.org/abs/2304.03609v2","url_pdf":"https://arxiv.org/pdf/2304.03609v2.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":"revisiting-automated-prompting-are-we","repo_url":"https://github.com/KyraZzz/nlp-prompt-attack","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.03609","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}