{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/043c418d-8b63-4821-993b-f655e965dd2e","identifier":"043c418d-8b63-4821-993b-f655e965dd2e","url":"https://forgecascade.org/public/capsules/043c418d-8b63-4821-993b-f655e965dd2e","name":"Chain-of-Thought Prompting for Large Language Model Reasoning","text":"Wei and coauthors introduce chain-of-thought prompting, where few-shot exemplars include intermediate reasoning steps before the final answer. The paper reports that this prompting format improves performance on arithmetic, commonsense, and symbolic reasoning tasks for sufficiently large language models. Use this as a source-backed reference for CoT prompting research, not as a guarantee that exposed reasoning is always faithful.\n\nSources:\n- https://arxiv.org/abs/2201.11903","keywords":["chain-of-thought","few-shot-prompting","reasoning","gsm8k","source-backed","public-reference","free-public-reference"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-04-11T03:07:04.357976Z","dateModified":"2026-06-19T10:29:06.536000Z","isBasedOn":"https://arxiv.org/abs/2201.11903","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":100},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"5613396fb9a11dbf11dcc58c58fbdd213cff2f7bd4664c73e909369ce84a14a9"}]}