Papers › Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

28 Jan 2022arXiv:2201.11903archive 2025-07-28

Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, Denny Zhou

We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2201.11903")

Code

Syntology Ran 2 of 7 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 7 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

19 repositories listed; official and paper-mentioned ones first.

TianduoWang/MsAT mentioned on GitHubpytorchMIT report
guidance-ai/guidance mentioned on GitHubMIT report
imnearth/coat mentioned on GitHub report
infini-ai-lab/sirius mentioned on GitHubpytorch report
lupantech/chameleon-llm mentioned on GitHub report
mbzuai-clear/ioe-prompting mentioned on GitHub report
microsoft/guidance mentioned on GitHubMIT report
mrlab-ai/NL2Plan mentioned on GitHubGPL-3.0 report
nicolay-r/thor-ecac mentioned on GitHubpytorch report
rlqja1107/torch-LLM4SGG mentioned on GitHubpytorch report
scofield7419/thor-isa mentioned on GitHubpytorchApache-2.0 report
srush/minichain mentioned on GitHubpytorchMIT report
sunlab-osu/understanding-cot mentioned on GitHubpytorch report
thu-keg/korc mentioned on GitHubpytorchMIT report
thudm/chatglm2-6b mentioned on GitHubpytorchNOASSERTION report
yinzhangyue/AoR mentioned on GitHubApache-2.0 report
yinzhangyue/eot mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran
5unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ChainOfThoughtCause nicolay-r/thor-ecac/src/cot_cause.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · da9673a8a47a19c8 · report
get_combination_mask TianduoWang/MsAT/deductreasoner/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 57cd245fea675806 · report
calculate_acc TianduoWang/MsAT/core/utils.py community (archive-listed) unverified MIT (permissive) · ed156b3a46d11ab3 · report
calculate_acc_code TianduoWang/MsAT/core/utils.py community (archive-listed) unverified MIT (permissive) · 2643a333e4f14f19 · report
count_parameters TianduoWang/MsAT/core/utils.py community (archive-listed) unverified MIT (permissive) · cbf3e12d7057a165 · report
get_batched_prediction_consider_multiple_m0 TianduoWang/MsAT/deductreasoner/trainer.py community (archive-listed) unverified MIT (permissive) · 5961e81f95a87056 · report
get_train_dataloader TianduoWang/MsAT/deductreasoner/prepare_dataset.py community (archive-listed) unverified MIT (permissive) · 10a9e1bd9dab41c9 · report

Tasks

Common Sense ReasoningGSM8KLanguage ModelingLanguage ModellingMathQuestion Answering

Datasets

Introduced by this paper, per the archive.

LastLetterConcat

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning CommonsenseQA Chain of thought ASDiv Accuracy 28.6 #37 of 38 Archive leaderboard report
Question Answering WebQuestions CoT EM 42.5 #15 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CoT Prompting

AdamAttentionAttention DropoutBPECoT PromptingCosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections