# Get an A in Math: Progressive Rectification Prompting

arXiv: https://arxiv.org/abs/2312.06867 · HTML: https://mlsanity.com/paper/2312.06867/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Generate & Rank: A Multi-task Framework for Math Word Problems](https://mlsanity.com/paper/2109.03034/) (2021)
- [IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions](https://mlsanity.com/paper/2305.14010/) (2023)
- [Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models](https://mlsanity.com/paper/2310.13127/) (2023)
- [Generalizing Math Word Problem Solvers via Solution Diversification](https://mlsanity.com/paper/2212.00833/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges](https://mlsanity.com/paper/2412.11936/) (2024)
- [Large Language Models Can Self-Correct with Key Condition Verification](https://mlsanity.com/paper/2405.14092/) (2024)
- [Toward Adaptive Reasoning in Large Language Models with Thought Rollback](https://mlsanity.com/paper/2412.19707/) (2024)
- [Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization](https://mlsanity.com/paper/2508.17976/) (2025)
- [From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision](https://mlsanity.com/paper/2509.24351/) (2025)
- [Solving Math Word Problems Using Estimation Verification and Equation Generation](https://mlsanity.com/paper/2509.18565/) (2025)

## Abstract (arXiv)

Chain-of-Thought (CoT) prompting methods have enabled large language models (LLMs) to generate reasoning paths and solve math word problems (MWPs). However, they are sensitive to mistakes in the paths, as any mistake can result in an incorrect answer. We propose a novel method named Progressive Rectification Prompting (PRP) to improve average accuracy on eight MWP datasets from 77.3 to 90.5. Given an initial answer from CoT, PRP iterates a verify-then-rectify process to progressively identify incorrect answers and rectify the reasoning paths. With the most likely correct answer, the LLM predicts a masked numerical value in the question; if the prediction does not match the masked value, the answer is likely incorrect. Then the LLM is prompted to re-generate the reasoning path hinted with a set of incorrect answers to prevent itself from repeating previous mistakes. PRP achieves the best performance compared against the CoT methods. Our implementation is made publicly available at https://wzy6642.github.io/prp.github.io/.