{"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/shepherd-pre-trained-language-models-to","title":"Iteratively Prompt Pre-trained Language Models for Chain of Thought","arxiv_id":"2203.08383","date":"2022-03-16","proceeding":null,"authors":["Boshi Wang","Xiang Deng","Huan Sun"],"abstract":"While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a \"chain of thought\" for these tasks, how can we equip PLMs with such abilities? In this work, we explore an iterative prompting framework, a new prompting paradigm which progressively elicits relevant knowledge from PLMs for multi-step inference. We identify key limitations of existing prompting methods, namely they are either restricted to queries with a single identifiable relation/predicate, or being agnostic to input contexts, which makes it difficult to capture variabilities across different inference steps. We propose an iterative context-aware prompter, which addresses these limitations by learning to dynamically synthesize prompts conditioned on the current step's contexts. Experiments on three datasets involving multi-step reasoning show the effectiveness of the iterative scheme and the context-aware prompter design.","url_abs":"https://arxiv.org/abs/2203.08383v3","url_pdf":"https://arxiv.org/pdf/2203.08383v3.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":"shepherd-pre-trained-language-models-to","repo_url":"https://github.com/sunlab-osu/iterprompt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.08383","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}