{"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/language-models-are-multilingual-chain-of","title":"Language Models are Multilingual Chain-of-Thought Reasoners","arxiv_id":"2210.03057","date":"2022-10-06","proceeding":null,"authors":["Freda Shi","Mirac Suzgun","Markus Freitag","Xuezhi Wang","Suraj Srivats","Soroush Vosoughi","Hyung Won Chung","Yi Tay","Sebastian Ruder","Denny Zhou","Dipanjan Das","Jason Wei"],"abstract":"We evaluate the reasoning abilities of large language models in multilingual settings. We introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating 250 grade-school math problems from the GSM8K dataset (Cobbe et al., 2021) into ten typologically diverse languages. We find that the ability to solve MGSM problems via chain-of-thought prompting emerges with increasing model scale, and that models have strikingly strong multilingual reasoning abilities, even in underrepresented languages such as Bengali and Swahili. Finally, we show that the multilingual reasoning abilities of language models extend to other tasks such as commonsense reasoning and word-in-context semantic judgment. The MGSM benchmark is publicly available at https://github.com/google-research/url-nlp.","url_abs":"https://arxiv.org/abs/2210.03057v1","url_pdf":"https://arxiv.org/pdf/2210.03057v1.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":"language-models-are-multilingual-chain-of","repo_url":"https://github.com/google-research/url-nlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"language-models-are-multilingual-chain-of","repo_url":"https://github.com/laihuiyuan/mcot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"language-models-are-multilingual-chain-of","repo_url":"https://github.com/microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-models-are-multilingual-chain-of","repo_url":"https://github.com/opendatalab/charm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[{"slug":"mgsm","name":"MGSM","full_name":"Multilingual Grade School Math"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.03057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}