Research map / Large language models / Reasoning and chain of thought
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| chain-of-thought exemplars instead of standard few-shot | PaLM 540B · GSM8K | accuracy: 17.9 -> 56.9 | Helped |
| chain-of-thought prompting at small scale | UL2 20B · GSM8K | accuracy: 4.1 -> 4.4 | No clear effect |
| chain-of-thought prompting | LaMDA 137B · AQuA | accuracy: 25.5 -> 20.6 | Hurt |
| chain-of-thought prompting | Codex · GSM8K | accuracy: 19.7 -> 63.1 | Helped |
| add post-hoc external calculator (ablation) | PaLM 540B chain of thought · GSM8K | accuracy: 56.9 -> 58.6 | Helped |
| replace chain of thought with equation-only intermediate step (ablation) | LaMDA 137B · GSM8K | accuracy | Hurt |
Closest papers by meaning
- Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns (AAAI 2025 · similarity 0.94)
- Large Language Models as Analogical Reasoners (ICLR 2024 · similarity 0.92)
- Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models (ICLR 2024 · similarity 0.92)
- THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS (ICLR 2024 · similarity 0.91)
- Chain of Thoughtlessness? An Analysis of CoT in Planning (NeurIPS 2024 · similarity 0.91)
- SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought (NeurIPS 2025 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.