中文
相关论文

相关论文: GT-HarmBench: Benchmarking AI Safety Risks Through…

200 篇论文

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…

计算与语言 · 计算机科学 2026-03-10 Weixiang Zhao , Haozhen Li , Yanyan Zhao , xuda zhi , Yongbo Huang , Hao He , Bing Qin , Ting Liu

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

人工智能 · 计算机科学 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…

人工智能 · 计算机科学 2026-03-17 Changyi Li , Pengfei Lu , Xudong Pan , Fazl Barez , Min Yang

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

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…

计算机与社会 · 计算机科学 2026-05-19 Miles Q. Li , Benjamin C. M. Fung , Boyang Li , Heba Ismail , Farkhund Iqbal

Developing safe, aligned agentic AI systems requires comprehensive empirical testing, yet many existing benchmarks neglect crucial themes aligned with biology and economics, both time-tested fundamental sciences describing our needs and…

多智能体系统 · 计算机科学 2025-12-01 Roland Pihlakas

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…

人工智能 · 计算机科学 2026-02-10 Cheol Woo Kim , Davin Choo , Tzeh Yuan Neoh , Milind Tambe

Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language models (LLMs) and vision language models (VLMs) now assist in…

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

计算与语言 · 计算机科学 2025-05-21 Zhexin Zhang , Shiyao Cui , Yida Lu , Jingzhuo Zhou , Junxiao Yang , Hongning Wang , Minlie Huang

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

计算与语言 · 计算机科学 2026-03-04 Adi Simhi , Jonathan Herzig , Martin Tutek , Itay Itzhak , Idan Szpektor , Yonatan Belinkov

Evaluating AI agents in finance faces two key challenges: static benchmarks require costly expert annotation yet miss the dynamic decision-making central to real-world trading, while LLM-based judges introduce uncontrolled variance on…

人工智能 · 计算机科学 2026-03-03 Xiaochuang Yuan , Hui Xu , Silvia Xu , Cui Zou , Jing Xiong

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…

计算机与社会 · 计算机科学 2025-11-27 Udari Madhushani Sehwag , Shayan Shabihi , Alex McAvoy , Vikash Sehwag , Yuancheng Xu , Dalton Towers , Furong Huang

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier…

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

人工智能 · 计算机科学 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko

The rapid proliferation and deployment of General-Purpose AI (GPAI) models, including large language models (LLMs), present unprecedented challenges for AI supervisory entities. We hypothesize that these entities will need to navigate an…

人工智能 · 计算机科学 2025-06-12 Manuel Cebrian , Emilia Gomez , David Fernandez Llorca

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users'…

计算与语言 · 计算机科学 2025-10-21 Youliang Yuan , Wenxiang Jiao , Yuejin Xie , Chihao Shen , Menghan Tian , Wenxuan Wang , Jen-tse Huang , Pinjia He

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

机器学习 · 计算机科学 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv
‹ 上一页 1 2 3 10 下一页 ›