arXiv Computation and Language September 2, 2026 By Sagnik Basu, Subhrajit Mitra, Aman Juneja, Somnath Banerjee, Rima Hazra, Animesh Mukherjee

SafeMath: Safe Solutions for Unsafe Math Word Problems

Read the original on arXiv Computation and Language →

The paper introduces ToxicGSM, a dataset of 1.9k arithmetic problems that embed harmful or sensitive context while keeping the math reasoning intact. It audits current large language models (LLMs) on this dataset, revealing how math word problems can subtly propagate bias, unethical, or psychologically harmful content, especially in educational settings for children. The authors propose SafeMath, a safety alignment technique that reduces harmful outputs without sacrificing, and sometimes improving, mathematical reasoning performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Sep 1

SafeMath: Inference-time Safety improves Math Accuracy

arXiv:2603.25201v2 Announce Type: replace Abstract: Recent research points toward LLMs being manipulated through adversarial and seemingly benign inputs, resulting in harmful, biased, or policy-viola...

By Sagnik Basu, Subhrajit Mitra, Aman Juneja, Somnath Banerjee, Rima Hazra, Animesh Mukherjee

llms safety

arXiv AI

4d ago

Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

arXiv:2609.36254v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning bef...

By Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan, Alexander Kotov, Dongxiao Zhu

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 26

HauntAttack: When Attack Follows Reasoning as a Shadow

arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.

By Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui

safety

arXiv Computation and Language

Sep 24

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

SafeTutors is a benchmark designed to evaluate both safety and pedagogical effectiveness of AI tutoring systems across mathematics, physics, and chemistry. It introduces a risk taxonomy of 11 harm dimensions and 48 sub‑risks based on learning‑science literature, focusing on issues such as answer over‑disclosure, misconception reinforcement, and loss of scaffolding. The study finds that all tested models exhibit broad harms, that larger scale does not mitigate these issues, and that multi‑turn interactions significantly increase pedagogical failures from 17.7% to 77.8%.

By Rima Hazra, Bikram Ghuku, Ilona Marchenko, Yaroslava Tokarieva, Sayan Layek, Somnath Banerjee, Julia Stoyanovich, Mykola Pechenizkiy

llms benchmarks safety

Hugging Face Trending Papers

Jun 4

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.

llms reinforcement-learning safety

arXiv Machine Learning

Jul 24

Concept Concentration for Faithful Representation Intervention

arXiv:2505. 18672v2 Announce Type: replace Abstract: Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to elicit the aligned and expected behaviors.

By Hongzheng Yang, Yongqiang Chen, Zeyu Qin, Tongliang Liu, Chaowei Xiao, Kun Zhang, Bo Han