English
Related papers

Related papers: DeceptGuard :A Constitutional Oversight Framework …

200 papers

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their…

Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xiaoya Lu , Yijin Zhou , Zeren Chen , Ruocheng Wang , Bingrui Sima , Enshen Zhou , Lu Sheng , Dongrui Liu , Jing Shao

Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large models (GPT-5, Gemini-3-Flash) can serve as effective CoT…

Cryptography and Security · Computer Science 2026-05-14 Nirav Diwan , Han Wang , Berkcan Kapusuzoglu , Ramin Moradi , Supriyo Chakraborty , Giri Iyengar , Sambit Sahu , Huan Zhang , Gang Wang

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Computation and Language · Computer Science 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visual, and textual-across four multimodal benchmarks and two…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yizhuo Ding , Mingkang Chen , Zhibang Feng , Tong Xiao , Wanying Qu , Wenqi Shao , Yanwei Fu

Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral…

Computation and Language · Computer Science 2026-05-28 Hyeonjeong Ha , Jeonghwan Kim , Cheng Qian , Jiayu Liu , William M. Campbell , Yue Wu , Yuji Zhang , Kathleen McKeown , Dilek Hakkani-Tur , Heng Ji

Recently, given the docstring for the target problem and the target function signature, large language models (LLMs) have been used not only to generate source code, but also to generate test cases, consisting of test inputs and assertions…

Software Engineering · Computer Science 2025-01-07 Hao Yu , Tianyu Chen , Jiaming Huang , Zongyang Li , Dezhi Ran , Xinyu Wang , Ying Li , Assaf Marron , David Harel , Yuan Xie , Tao Xie

Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs -- a phenomenon known as \emph{latent knowledge}. Existing…

Computation and Language · Computer Science 2026-05-29 Ji-jun Park , Soo-joon Choi , Jiwon Jeong , Taeyang Yoon , Ju-Wan Lee

Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix monitors over heterogeneous traces, but hand-authored event…

Artificial Intelligence · Computer Science 2026-05-08 Xinmiao Huang , Jinwei Hu , Rajarshi Roy , Changshun Wu , Yi Dong , Xiaowei Huang

Assessing the capacity of Large Language Models (LLMs) to plan and reason within the constraints of interactive environments is crucial for developing capable AI agents. We introduce $\textbf{LLM-BabyBench}$, a new benchmark suite designed…

Artificial Intelligence · Computer Science 2025-05-20 Omar Choukrani , Idriss Malek , Daniil Orel , Zhuohan Xie , Zangir Iklassov , Martin Takáč , Salem Lahlou

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these…

Computation and Language · Computer Science 2026-03-23 Weilin Zhou , Shanwen Tan , Enhao Gu , Yurong Qian

Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm…

Artificial Intelligence · Computer Science 2026-01-23 Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Sungryull Sohn , Yunxiang Zhang , Moontae Lee , Hao Peng , Lu Wang , Honglak Lee

As software grows in complexity to accommodate diverse features and platforms, software bloating has emerged as a significant challenge, adversely affecting performance and security. However, existing approaches inadequately address the…

Software Engineering · Computer Science 2025-03-13 Bo Lin , Shangwen Wang , Yihao Qin , Liqian Chen , Xiaoguang Mao

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised…

Artificial Intelligence · Computer Science 2026-04-28 Rui Miao , Yixin Liu , Yili Wang , Xu Shen , Yue Tan , Yiwei Dai , Shirui Pan , Xin Wang

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

Machine Learning · Computer Science 2026-04-07 Lin Wang , Junfeng Fang , Dan Zhang , Fei Shen , Xiang Wang , Tat-Seng Chua

As deep learning models are widely used in software systems, test generation plays a crucial role in assessing the quality of such models before deployment. To date, the most advanced test generators rely on generative AI to synthesize…

Software Engineering · Computer Science 2026-01-21 Xingcheng Chen , Oliver Weissl , Andrea Stocco

The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool…

Artificial Intelligence · Computer Science 2026-03-06 Zhipeng Chen , Zhongrui Zhang , Chao Zhang , Yifan Xu , Lan Yang , Jun Liu , Ke Li , Yi-Zhe Song

E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs…

Computation and Language · Computer Science 2026-05-28 Ancheng Xu , Zhihao Yang , Jingpeng Li , Guanghu Yuan , Longze Chen , Liang Yan , Jiehui Zhou , Zhen Qin , Hengyu Chang , Yukun Chen , Hamid Alinejad-Rokny , Min Yang

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian