English
Related papers

Related papers: A Granular Study of Safety Pretraining under Model…

200 papers

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue…

Artificial Intelligence · Computer Science 2026-04-22 Yeonjun In , Wonjoong Kim , Sangwu Park , Chanyoung Park

The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model's output, hoping for a responsive model that can complete responses according to their…

Computation and Language · Computer Science 2024-07-25 Jianhao Yan , Yun Luo , Yue Zhang

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Machine Learning · Computer Science 2025-10-28 Taeyoun Kim , Fahim Tajwar , Aditi Raghunathan , Aviral Kumar

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Computation and Language · Computer Science 2024-05-03 Mansi Phute , Alec Helbling , Matthew Hull , ShengYun Peng , Sebastian Szyller , Cory Cornelius , Duen Horng Chau

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

Machine Learning · Computer Science 2025-06-03 Jakub Łucki , Boyi Wei , Yangsibo Huang , Peter Henderson , Florian Tramèr , Javier Rando

Ambiguity in natural language instructions poses significant risks in safety-critical human-robot interaction, particularly in domains such as surgery. To address this, we propose a framework that uses Large Language Models (LLMs) for…

Robotics · Computer Science 2025-07-16 Ana Davila , Jacinto Colan , Yasuhisa Hasegawa

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Computation and Language · Computer Science 2026-03-05 Yuxiao Lu , Lin Xu , Yang Sun , Wenjun Li , Jie Shi

As LLMs enter conflict monitoring, understanding systematic distortions in their outputs is critical for humanitarian accountability. We evaluate four vanilla open-weight models Gemma 3 4B, Llama 3.2 3B, Mistral 7B, and OLMo 2 7B and two…

Computation and Language · Computer Science 2026-05-07 Hoffmann Muki , Olukunle Owolabi

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we…

Cryptography and Security · Computer Science 2026-01-22 Luis Lazo , Hamed Jelodar , Roozbeh Razavi-Far

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Cryptography and Security · Computer Science 2026-02-27 Piyush Jaiswal , Aaditya Pratap , Shreyansh Saraswati , Harsh Kasyap , Somanath Tripathy

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Computation and Language · Computer Science 2026-05-15 Yu Fu , Haz Sameen Shahgir , Huanli Gong , Zhipeng Wei , N. Benjamin Erichson , Yue Dong

Large Language Models (LLMs) are increasingly consulted for high-stakes life advice, yet they lack standard safeguards against providing confident but misguided responses. This creates risks of sycophancy and over-confidence. This paper…

Artificial Intelligence · Computer Science 2025-07-30 Joshua Adrian Cahyono , Saran Subramanian

Large Language Models (LLMs) often produce hallucinated or unverifiable content, undermining their reliability in factual domains. This work investigates Reinforcement Learning with Verifiable Rewards (RLVR) as a training paradigm that…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Cryptography and Security · Computer Science 2024-12-10 Bryan Li , Sounak Bagchi , Zizhan Wang

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design…

Computation and Language · Computer Science 2024-07-03 Melanie Sclar , Yejin Choi , Yulia Tsvetkov , Alane Suhr

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This…

Cryptography and Security · Computer Science 2024-12-03 Jie Li , Yi Liu , Chongyang Liu , Xiaoning Ren , Ling Shi , Weisong Sun , Yinxing Xue

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Computation and Language · Computer Science 2025-10-07 Ken Tsui

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan