English
Related papers

Related papers: Simple Role Assignment is Extraordinarily Effectiv…

200 papers

The rapid advancement of large language models (LLMs) has intensified concerns about the robustness of their safety alignment. While existing jailbreak studies explore both single-turn and multi-turn strategies, most implicitly assume a…

Artificial Intelligence · Computer Science 2025-12-23 Jianyi Zhang , Shizhao Liu , Ziyin Zhou , Zhen Li

We present a modular, explainable LLM-agent pipeline for decision support that externalizes reasoning into auditable artifacts. The system instantiates three frameworks: Vester's Sensitivity Model (factor set, signed impact matrix, systemic…

Artificial Intelligence · Computer Science 2025-11-11 Marcel Pehlke , Marc Jansen

With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…

Artificial Intelligence · Computer Science 2025-07-02 Siyuan Liang , Tianmeng Fang , Zhe Liu , Aishan Liu , Yan Xiao , Jinyuan He , Ee-Chien Chang , Xiaochun Cao

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,…

Computation and Language · Computer Science 2026-03-10 Weixiang Zhao , Haozhen Li , Yanyan Zhao , xuda zhi , Yongbo Huang , Hao He , Bing Qin , Ting Liu

When an AI system interacts with multiple users, it frequently needs to make allocation decisions. For instance, a virtual agent decides whom to pay attention to in a group setting, or a factory robot selects a worker to deliver a part.…

Machine Learning · Computer Science 2019-12-18 Yifang Chen , Alex Cuellar , Haipeng Luo , Jignesh Modi , Heramb Nemlekar , Stefanos Nikolaidis

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection of AI safety, moral philosophy, and cognitive science. We introduce Morality Chains, a novel…

Large language models (LLMs) are increasingly used to simulate human behavior in experimental settings, but they systematically diverge from human decisions in complex decision-making environments, where participants must anticipate others'…

Artificial Intelligence · Computer Science 2026-01-06 Letian Kong , Qianran , Jin , Renyu Zhang

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Computation and Language · Computer Science 2025-06-05 Chak Tou Leong , Qingyu Yin , Jian Wang , Wenjie Li

Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those…

Machine Learning · Computer Science 2022-12-13 Linrui Zhang , Qin Zhang , Li Shen , Bo Yuan , Xueqian Wang , Dacheng Tao

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…

Cryptography and Security · Computer Science 2026-04-24 Rui Yang Tan , Yujia Hu , Roy Ka-Wei Lee

Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k…

Computation and Language · Computer Science 2024-11-08 Dawei Zhu , Liang Wang , Nan Yang , Yifan Song , Wenhao Wu , Furu Wei , Sujian Li

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Perception components in autonomous systems are often developed and optimized independently of downstream decision-making and control components, relying on established performance metrics like accuracy, precision, and recall. Traditional…

Robotics · Computer Science 2024-12-05 Weisi Fan , Jesse Lane , Qisai Liu , Soumik Sarkar , Tichakorn Wongpiromsarn

Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context to identify and mitigate potential risks. Though researchers…

Computation and Language · Computer Science 2026-04-15 Haoran Li , Yulin Chen , Huihao Jing , Wenbin Hu , Tsz Ho Li , Chanhou Lou , Hong Ting Tsang , Sirui Han , Yangqiu Song

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Artificial Intelligence · Computer Science 2026-02-10 Anselm Paulus , Ilia Kulikov , Brandon Amos , Rémi Munos , Ivan Evtimov , Kamalika Chaudhuri , Arman Zharmagambetov

The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduces substantial unintentional behavioral safety risks.…

Artificial Intelligence · Computer Science 2026-03-30 Yuxuan Li , Yi Lin , Peng Wang , Shiming Liu , Xuetao Wei

The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback…

Machine Learning · Computer Science 2024-09-20 Eduardo Pignatelli , Johan Ferret , Tim Rockäschel , Edward Grefenstette , Davide Paglieri , Samuel Coward , Laura Toni

Goal-conditioned policies, such as those learned via imitation learning, provide an easy way for humans to influence what tasks robots accomplish. However, these robot policies are not guaranteed to execute safely or to succeed when faced…

Robotics · Computer Science 2025-03-05 Hyun Joe Jeong , Rosy Chen , Andrea Bajcsy