English
Related papers

Related papers: AI Sandbagging: Language Models can Strategically …

200 papers

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-Bench, provide standardized and transparent evaluation protocols that support comparative analysis, reproducibility, and systematic progress tracking in Language Model (LM)…

Computation and Language · Computer Science 2026-01-08 Md. Najib Hasan , Md Mahadi Hassan Sibat , Mohammad Fakhruddin Babar , Souvika Sarkar , Monowar Hasan , Santu Karmaker

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from…

Computation and Language · Computer Science 2023-11-02 Haoran Li , Dadi Guo , Wei Fan , Mingshi Xu , Jie Huang , Fanpu Meng , Yangqiu Song

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

When training powerful AI systems to perform complex tasks, it may be challenging to provide training signals which are robust to optimization. One concern is \textit{measurement tampering}, where the AI system manipulates multiple…

Machine Learning · Computer Science 2023-10-02 Fabien Roger , Ryan Greenblatt , Max Nadeau , Buck Shlegeris , Nate Thomas

Large language model personalization typically adapts outputs to user preferences and style but does not account for differences in user evaluation capacity across domains of expertise. This limitation can encourage Professional Domain…

Computation and Language · Computer Science 2026-05-18 Sen Yang , Yinglei Ma

Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can…

Computation and Language · Computer Science 2024-01-25 Yi Zeng , Hongpeng Lin , Jingwen Zhang , Diyi Yang , Ruoxi Jia , Weiyan Shi

The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds of billions of…

Machine Learning · Computer Science 2025-11-24 Maximilian Abstreiter , Sasu Tarkoma , Roberto Morabito

Access to mental health support remains limited, particularly in marginalized communities where structural and cultural barriers hinder timely care. This paper explores the potential of AI-enabled chatbots as a scalable solution, focusing…

Computers and Society · Computer Science 2024-10-07 Rawan AlMakinah , Andrea Norcini-Pala , Lindsey Disney , M. Abdullah Canbaz

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, few studies have addressed the LLM threat and vulnerability from an ideology perspective, especially when they are…

Computation and Language · Computer Science 2023-09-29 Xiaotian Zhou , Qian Wang , Xiaofeng Wang , Haixu Tang , Xiaozhong Liu

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Cryptography and Security · Computer Science 2025-05-29 Yao Huang , Yitong Sun , Shouwei Ruan , Yichi Zhang , Yinpeng Dong , Xingxing Wei

The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is…

Computation and Language · Computer Science 2026-01-30 Devanshu Sahoo , Manish Prasad , Vasudev Majhi , Arjun Neekhra , Yash Sinha , Murari Mandal , Vinay Chamola , Dhruv Kumar

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Human-Computer Interaction · Computer Science 2025-04-04 Abed Kareem Musaffar , Anand Gokhale , Sirui Zeng , Rasta Tadayon , Xifeng Yan , Ambuj Singh , Francesco Bullo

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these…

Artificial Intelligence · Computer Science 2023-08-08 Shuang Ao

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Computation and Language · Computer Science 2025-05-16 Michael Fire , Yitzhak Elbazis , Adi Wasenstein , Lior Rokach

Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber…

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…

Artificial Intelligence · Computer Science 2026-04-07 Anshuman Chhabra , Shrestha Datta , Shahriar Kabir Nahin , Prasant Mohapatra

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study…

Cryptography and Security · Computer Science 2025-03-05 Hang Zhang , Qian Lou , Yanshan Wang