English
Related papers

Related papers: PropensityBench: Evaluating Latent Safety Risks in…

200 papers

Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary between harmful and harmless content. Existing benchmarks rely…

Computation and Language · Computer Science 2025-10-23 Sophia Xiao Pu , Sitao Cheng , Xin Eric Wang , William Yang Wang

The robust safety of Vision-Language Large Models (VLLMs) against joint multilingual and multimodal threats remains severely underexplored. Current benchmarks typically isolate these dimensions, being either multilingual but text-only, or…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Enyi Shi , Pengyang Shao , Yanxin Zhang , Chenhang Cui , Jiayi Lyu , Xiaobo Xia , Fei Shen , Tat-Seng Chua

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Cryptography and Security · Computer Science 2026-05-14 Zvi Topol

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

Artificial Intelligence · Computer Science 2026-04-14 Keita Broadwater

As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained on text corpora reliably reason about complex physics while adhering to safety…

Artificial Intelligence · Computer Science 2026-04-13 Yalun Wu , Haotian Liu , Zhoujun Li , Boyang Wang

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

As Language Models (LMs) increasingly operate as autonomous agents, accurately forecasting their capabilities becomes crucial for societal preparedness. We evaluate six forecasting methods that predict downstream capabilities of LM agents.…

Computation and Language · Computer Science 2025-03-04 Govind Pimpale , Axel Højmark , Jérémy Scheurer , Marius Hobbhahn

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Cryptography and Security · Computer Science 2026-05-27 Faruk Alpay , Taylan Alpay

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Cryptography and Security · Computer Science 2025-11-13 Daniyal Ganiuly , Assel Smaiyl

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

Cryptography and Security · Computer Science 2026-01-16 Yi Liu , Weizhe Wang , Ruitao Feng , Yao Zhang , Guangquan Xu , Gelei Deng , Yuekang Li , Leo Zhang

As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria like helpfulness…

The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…

Computers and Society · Computer Science 2026-05-19 Miles Q. Li , Benjamin C. M. Fung , Boyang Li , Heba Ismail , Farkhund Iqbal

Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…

Artificial Intelligence · Computer Science 2026-02-03 Xuan Liu , Haoyang Shang , Zizhang Liu , Xinyan Liu , Yunze Xiao , Yiwen Tu , Haojian Jin

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

Large language models (LLMs) have witnessed rapid advancements, demonstrating remarkable capabilities. However, a notable vulnerability persists: LLMs often uncritically accept flawed or contradictory premises, leading to inefficient…

Computation and Language · Computer Science 2025-11-25 Jinzhe Li , Gengxu Li , Yi Chang , Yuan Wu

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

Computation and Language · Computer Science 2023-04-21 Hao Sun , Zhexin Zhang , Jiawen Deng , Jiale Cheng , Minlie Huang

As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is…

Artificial Intelligence · Computer Science 2023-12-25 Zeyu Gao , Hao Wang , Yuchen Zhou , Wenyu Zhu , Chao Zhang

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

Cryptography and Security · Computer Science 2026-02-10 Sai Puppala , Ismail Hossain , Md Jahangir Alam , Yoonpyo Lee , Jay Yoo , Tanzim Ahad , Syed Bahauddin Alam , Sajedul Talukder

Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance personalization in future conversations. However, the same…

Artificial Intelligence · Computer Science 2026-02-03 Sidharth Pulipaka , Oliver Chen , Manas Sharma , Taaha S Bajwa , Vyas Raina , Ivaxi Sheth