# RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought

arXiv: https://arxiv.org/abs/2305.11499 · HTML: https://mlsanity.com/paper/2305.11499/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 48 references that are in the map.
- First posted on arXiv 19 May 2023.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 8 of 8)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)

## Built on by (most cited first, 30 of 47)

- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://mlsanity.com/paper/2502.01839/) (2025)
- [Forward-Backward Reasoning in Large Language Models for Mathematical Verification](https://mlsanity.com/paper/2308.07758/) (2023)
- [Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning](https://mlsanity.com/paper/2410.17885/) (2024)
- [Reverse Thinking Makes LLMs Stronger Reasoners](https://mlsanity.com/paper/2411.19865/) (2024)
- [Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text](https://mlsanity.com/paper/2403.05750/) (2024)
- [Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency](https://mlsanity.com/paper/2407.21443/) (2024)
- [Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains](https://mlsanity.com/paper/2506.02126/) (2025)
- [Learning to Plan for Language Modeling from Unlabeled Data](https://mlsanity.com/paper/2404.00614/) (2024)
- [AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models](https://mlsanity.com/paper/2310.00259/) (2023)
- [SQLucid: Grounding Natural Language Database Queries with Interactive Explanations](https://mlsanity.com/paper/2409.06178/) (2024)
- [Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling](https://mlsanity.com/paper/2409.11283/) (2024)
- [Towards A Unified View of Answer Calibration for Multi-Step Reasoning](https://mlsanity.com/paper/2311.09101/) (2023)
- [Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information](https://mlsanity.com/paper/2408.10615/) (2024)
- [Enabling Language Models to Implicitly Learn Self-Improvement](https://mlsanity.com/paper/2310.00898/) (2023)
- [An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide](https://mlsanity.com/paper/2402.14837/) (2024)
- [Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models](https://mlsanity.com/paper/2410.13413/) (2024)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree](https://mlsanity.com/paper/2510.13363/) (2025)
- [Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents](https://mlsanity.com/paper/2602.10356/) (2026)
- [On the Discussion of Large Language Models: Symmetry of Agents and Interplay with Prompts](https://mlsanity.com/paper/2311.07076/) (2023)
- [DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs](https://mlsanity.com/paper/2401.05190/) (2024)
- [Learning to Ponder: Adaptive Reasoning in Latent Space](https://mlsanity.com/paper/2509.24238/) (2025)
- [Parameter-Efficient Tuning Helps Language Model Alignment](https://mlsanity.com/paper/2310.00819/) (2023)
- [Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries](https://mlsanity.com/paper/2403.01002/) (2024)
- [Deductive Additivity for Planning of Natural Language Proofs](https://mlsanity.com/paper/2307.02472/) (2023)
- [Has My System Prompt Been Used? Large Language Model Prompt Membership Inference](https://mlsanity.com/paper/2502.09974/) (2025)

## Abstract (arXiv)

Large language Models (LLMs) have achieved promising performance on arithmetic reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting. However, LLMs face challenges in maintaining factual consistency during reasoning, exhibiting tendencies to condition overlooking, question misinterpretation, and condition hallucination over given problems. Existing methods use coarse-grained feedback (e.g., whether the answer is correct) to improve factual consistency. In this work, we propose RCoT (Reversing Chain-of-Thought), a novel method to improve LLMs' reasoning abilities by automatically detecting and rectifying factual inconsistency in LLMs, generated solutions. To detect factual inconsistency, RCoT first asks LLMs to reconstruct the problem based on generated solutions. Then fine-grained comparisons between the original problem and the reconstructed problem expose the factual inconsistency in the original solutions. To rectify the solution, RCoT formulates detected factual inconsistency into fine-grained feedback to guide LLMs in revising solutions. Experimental results demonstrate improvements of RCoT over standard CoT, Self-Consistency and Self-Refine across seven arithmetic datasets. Moreover, we find that manually written fine-grained feedback can dramatically improve LLMs' reasoning abilities (e.g., ChatGPT reaches 94.6% accuracy on GSM8K), encouraging the community to further explore the fine-grained feedback generation methods.