SafeMath: Safe Solutions for Unsafe Math Word Problems

arXiv:2603.25201 · cs.CL, cs.CY · Submitted 2026-03-26 · Read on arXiv

cs.CL, cs.CY

Submitted: 2026-03-26

Updated: 2026-09-01

Comments: Accepted in EMNLP Findings 2026

Code: https://github.com/Swagnick99/SafeMath

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Alignment — 15× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Steering — 10× in this paper · explained in 2 episodes
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Inference-Time Steering — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adaptive Decoding — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Large Language Models for Mathematical Reasoning: Progresses and Challenges
• Constitutional AI: Harmlessness from AI Feedback
• Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
• Training Verifiers to Solve Math Word Problems
• Safe RLHF: Safe Reinforcement Learning from Human Feedback
• MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning
• Solving Math Word Problems by Combining Language Models With Symbolic Solvers
• Measuring Mathematical Problem Solving With the MATH Dataset
• Are NLP Models really able to Solve Simple Math Word Problems?
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Function Vectors in Large Language Models
• OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
• Qwen2 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering