Related papers: Model Capability Assessment and Safeguards for Bio…
With the steady rise of the use of AI in bio-technical applications and the widespread adoption of genomics sequencing, an increasing amount of AI-based algorithms and tools is entering the research and production stage affecting critical…
Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in…
AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
Generative Artificial Intelligence (AI) models such as OpenAI's ChatGPT have the potential to revolutionize Statistical Process Control (SPC) practice, learning, and research. However, these tools are in the early stages of development and…
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…
In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to cater to specific needs has opened new frontiers in AI…
As Large Language Models (LLMs) become increasingly autonomous and integrated into critical societal functions, the focus of AI safety must evolve from mitigating harmful content to evaluating underlying behavioral alignment. Current safety…
Systems like ChatGPT and Claude assist billions through proactive dialogue-offering unsolicited, task-relevant information. Drawing on Cognitive Load Theory, we study how cognitive load shapes performance in AI-assisted knowledge work. We…
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language…
There has been enormous interest in generative AI since ChatGPT was launched in 2022. However, there are concerns about the accuracy and consistency of the outputs of generative AI. We have carried out an exploratory study on the…
Given their ability for advanced reasoning, extensive contextual understanding, and robust question-answering abilities, large language models have become prominent in healthcare management research. Despite adeptly handling a broad…
We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the…
Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date medical knowledge and understanding of complex multimodal data. Gemini models, with strong general…
Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over…
How good a research scientist is ChatGPT? We systematically probed the capabilities of GPT-3.5 and GPT-4 across four central components of the scientific process: as a Research Librarian, Research Ethicist, Data Generator, and Novel Data…
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…
Scientific discovery is an inherently creative and uncertain process, requiring reasoning beyond the recall of known knowledge. While many benchmarks have been proposed to evaluate large language model (LLM) performance on deep research…