{"work":{"id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","openalex_id":null,"doi":null,"arxiv_id":"2205.11916","raw_key":null,"title":"Large Language Models are Zero-Shot Reasoners","authors":null,"authors_text":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa","year":2022,"venue":"cs.CL","abstract":"Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique for eliciting complex multi-step reasoning through step-by-step answer examples, achieved the state-of-the-art performances in arithmetics and symbolic reasoning, difficult system-2 tasks that do not follow the standard scaling laws for LLMs. While these successes are often attributed to LLMs' ability for few-shot learning, we show that LLMs are decent zero-shot reasoners by simply adding \"Let's think step by step\" before each answer. Experimental results demonstrate that our Zero-shot-CoT, using the same single prompt template, significantly outperforms zero-shot LLM performances on diverse benchmark reasoning tasks including arithmetics (MultiArith, GSM8K, AQUA-RAT, SVAMP), symbolic reasoning (Last Letter, Coin Flip), and other logical reasoning tasks (Date Understanding, Tracking Shuffled Objects), without any hand-crafted few-shot examples, e.g. increasing the accuracy on MultiArith from 17.7% to 78.7% and GSM8K from 10.4% to 40.7% with large InstructGPT model (text-davinci-002), as well as similar magnitudes of improvements with another off-the-shelf large model, 540B parameter PaLM. The versatility of this single prompt across very diverse reasoning tasks hints at untapped and understudied fundamental zero-shot capabilities of LLMs, suggesting high-level, multi-task broad cognitive capabilities may be extracted by simple prompting. We hope our work not only serves as the minimal strongest zero-shot baseline for the challenging reasoning benchmarks, but also highlights the importance of carefully exploring and analyzing the enormous zero-shot knowledge hidden inside LLMs before crafting finetuning datasets or few-shot exemplars.","external_url":"https://arxiv.org/abs/2205.11916","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-29T12:23:23.823461+00:00","pith_arxiv_id":"2205.11916","created_at":"2026-05-09T05:11:17.880826+00:00","updated_at":"2026-06-29T12:23:23.823461+00:00","title_quality_ok":true,"display_title":"Large Language Models are Zero-Shot Reasoners","render_title":"Large Language Models are Zero-Shot Reasoners"},"hub":{"state":{"work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":68,"external_cited_by_count":null,"distinct_field_count":12,"first_pith_cited_at":"2022-06-15T17:32:01+00:00","last_pith_cited_at":"2026-06-04T10:17:00+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-29T15:59:00.245827+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":14},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":14},{"context_polarity":"baseline","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}