Research map / Large language models / Reasoning and chain of thought
Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective
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 |
|---|---|---|---|
| add chain of thought to a 3-layer transformer (ablation) | 3-layer transformer · Arithmetic formula, 6 operators | accuracy (%): 17.72 -> 99.97 | Helped |
| add a layer without CoT (3 to 5 layers) (ablation) | transformer without CoT · Arithmetic formula, 6 operators | accuracy (%): 17.72 -> 46.19 | Helped |
| train on <=14 operators, test on longer formulas | 3-layer transformer with CoT · Arithmetic formula length generalization | accuracy (%): 99.9 -> 45.5 (15 to 18 operators) | Mixed |
Closest papers by meaning
- To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning (ICLR 2025 · similarity 0.92)
- Chain of Thoughtlessness? An Analysis of CoT in Planning (NeurIPS 2024 · similarity 0.92)
- How Does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding (AAAI 2026 · similarity 0.91)
- Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning (NeurIPS 2025 · similarity 0.91)
- Analyzing the Power of Chain of Thought through Memorization Capabilities (NeurIPS 2025 · similarity 0.91)
- Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns (AAAI 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.