# Adversarial Math Word Problem Generation

arXiv: https://arxiv.org/abs/2402.17916 · HTML: https://mlsanity.com/paper/2402.17916/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Analysing Mathematical Reasoning Abilities of Neural Models](https://mlsanity.com/paper/1904.01557/) (2019)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Deep Learning for Symbolic Mathematics](https://mlsanity.com/paper/1912.01412/) (2019)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [MathAttack: Attacking Large Language Models Towards Math Solving Ability](https://mlsanity.com/paper/2309.01686/) (2023)
- [Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams](https://mlsanity.com/paper/2310.08678/) (2023)
- [Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education](https://mlsanity.com/paper/2309.13059/) (2023)

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

- [Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies](https://mlsanity.com/paper/2502.08554/) (2025)
- [Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges](https://mlsanity.com/paper/2502.08680/) (2025)
- [NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning](https://mlsanity.com/paper/2509.23252/) (2025)
- [Elementary Math Word Problem Generation using Large Language Models](https://mlsanity.com/paper/2506.05950/) (2025)
- [A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation](https://mlsanity.com/paper/2601.11792/) (2026)
- [CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation](https://mlsanity.com/paper/2602.01660/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have significantly transformed the educational landscape. As current plagiarism detection tools struggle to keep pace with LLMs' rapid advancements, the educational community faces the challenge of assessing students' true problem-solving abilities in the presence of LLMs. In this work, we explore a new paradigm for ensuring fair evaluation -- generating adversarial examples which preserve the structure and difficulty of the original questions aimed for assessment, but are unsolvable by LLMs. Focusing on the domain of math word problems, we leverage abstract syntax trees to structurally generate adversarial examples that cause LLMs to produce incorrect answers by simply editing the numeric values in the problems. We conduct experiments on various open- and closed-source LLMs, quantitatively and qualitatively demonstrating that our method significantly degrades their math problem-solving ability. We identify shared vulnerabilities among LLMs and propose a cost-effective approach to attack high-cost models. Additionally, we conduct automatic analysis to investigate the cause of failure, providing further insights into the limitations of LLMs.