Research map / Large language models / Reasoning and chain of thought
Deductive Verification of Chain-of-Thought Reasoning
Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, Hao Su
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| verify each step with Natural Program decomposition instead of whole chain at once | ChatGPT verifier · Overall (6 datasets) | verification accuracy: 52% -> 69% | Improved |
| step-wise verification instead of whole-chain | ChatGPT verifier · Date | verification accuracy: 63% -> 73% | Improved |
| step-wise verification instead of whole-chain | ChatGPT verifier · Last Letters | verification accuracy: 51% -> 51% | No clear effect |
| use minimal necessary premises instead of full premises (ablation) | NP verification · Average (6 datasets) | verification accuracy: 57% -> 69% | Improved |
| one-shot prompt instead of zero-shot (ablation) | NP verification with minimal premises · Average (6 datasets) | verification accuracy: 53% -> 69% | Improved |
| increase Unanimity-Plurality Voting k' from 1 to 10 (ablation) | Deductive verification · AddSub | accuracy on correct-answer chains: 86% -> 92% | Improved |
| increase k' from 1 to 10 (ablation) | Deductive verification · AddSub | accuracy on wrong-answer chains: 38% -> 40% | No clear effect |
| add deductive verification and UPV filtering to Natural Program (ablation) | Natural Program · GSM8K | final answer accuracy: 87.05% -> 86.01% | Hurt |
| add deductive verification and UPV filtering to Natural Program (ablation) | Natural Program · AddSub | final answer accuracy: 93.67% -> 93.54% | No clear effect |
| Natural Program prompting instead of CoT + Voting | ChatGPT · Last Letters | final answer accuracy: 81.60% -> 92.98% | Improved |
| Natural Program prompting instead of CoT + Voting | ChatGPT · GSM8K | final answer accuracy: 87.62% -> 87.05% | No clear effect |
| fine-tune Vicuna-13B on deductive verification dataset | Vicuna-13B · Overall (6 datasets) | verification accuracy: 57% -> 66% | Improved |
Closest papers by meaning
- Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning (AAAI 2026 · similarity 0.91)
- Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning (NeurIPS 2025 · similarity 0.90)
- SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks (AAAI 2025 · similarity 0.90)
- Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation (ICLR 2025 · similarity 0.90)
- Verifying Chain-of-Thought Reasoning via Its Computational Graph (ICLR 2026 · similarity 0.90)
- The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think (ICLR 2026 · similarity 0.89)
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.
