English
Related papers

Related papers: STAIR: Improving Safety Alignment with Introspecti…

200 papers

Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…

Cryptography and Security · Computer Science 2025-04-08 Ziyang Li , Saikat Dutta , Mayur Naik

Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec…

Computation and Language · Computer Science 2025-10-07 Haoran Zhang , Yafu Li , Xuyang Hu , Dongrui Liu , Zhilin Wang , Bo Li , Yu Cheng

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering…

Computation and Language · Computer Science 2025-11-12 Zijun Wang , Haoqin Tu , Yuhan Wang , Juncheng Wu , Yanqing Liu , Jieru Mei , Brian R. Bartoldson , Bhavya Kailkhura , Cihang Xie

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which poses significant…

Machine Learning · Computer Science 2025-06-11 Zhenjiang Mao , Artem Bisliouk , Rohith Reddy Nama , Ivan Ruchkin

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), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools,…

Computation and Language · Computer Science 2025-07-30 Yifan Wei , Xiaoyan Yu , Yixuan Weng , Tengfei Pan , Angsheng Li , Li Du

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Artificial Intelligence · Computer Science 2025-10-02 Guobin Shen , Dongcheng Zhao , Haibo Tong , Jindong Li , Feifei Zhao , Yi Zeng

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…

Computation and Language · Computer Science 2025-11-21 Sangmook Lee , Dohyung Kim , Hyukhun Koh , Nakyeong Yang , Kyomin Jung

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Machine Learning · Computer Science 2025-02-04 Ching-Chia Kao , Chia-Mu Yu , Chun-Shien Lu , Chu-Song Chen

Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs…

Computation and Language · Computer Science 2026-03-10 Le Yu , Zhengyue Zhao , Yawen Zheng , Yunhao Liu

The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic…

Computation and Language · Computer Science 2025-09-29 Wenbin Hu , Huihao Jing , Haochen Shi , Haoran Li , Yangqiu Song

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

Artificial Intelligence · Computer Science 2025-10-27 Jingnan Zheng , Xiangtian Ji , Yijun Lu , Chenhang Cui , Weixiang Zhao , Gelei Deng , Zhenkai Liang , An Zhang , Tat-Seng Chua

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Computation and Language · Computer Science 2025-04-15 Shaoqing Zhang , Zhuosheng Zhang , Kehai Chen , Rongxiang Weng , Muyun Yang , Tiejun Zhao , Min Zhang

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

Cryptography and Security · Computer Science 2026-01-29 Xianglin Yang , Gelei Deng , Jieming Shi , Tianwei Zhang , Jin Song Dong

Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static heuristics or stochastic search, rendering them brittle…

Machine Learning · Computer Science 2026-05-22 Huilin Zhou , Jian Zhao , Yilu Zhong , Zhen Liang , Xiuyuan Chen , Yuchen Yuan , Tianle Zhang , Chi Zhang , Lan Zhang , Xuelong Li

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…

Cryptography and Security · Computer Science 2025-05-22 Taiye Chen , Zeming Wei , Ang Li , Yisen Wang

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by…

Machine Learning · Computer Science 2024-10-30 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Ling Liu