Related papers: Assessing Language Model Deployment with Risk Card…

Amidst escalating concerns about the detriments inflicted by AI systems, risk management assumes paramount importance, notably for high-risk applications as demanded by the European Union AI Act. Guidelines provided by ISO and NIST aim to…

Large language models (LLMs) have significantly transformed the landscape of Natural Language Processing (NLP). Their impact extends across a diverse spectrum of tasks, revolutionizing how we approach language understanding and generations.…

Organisations generate vast amounts of information, which has resulted in a long-term research effort into knowledge access systems for enterprise settings. Recent developments in artificial intelligence, in relation to large language…

Language models for code (CodeLMs) have emerged as powerful tools for code-related tasks, outperforming traditional methods and standard machine learning approaches. However, these models are susceptible to security vulnerabilities, drawing…

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case…

Context. Risk analysis assesses potential risks in specific scenarios. Risk analysis principles are context-less; the same methodology can be applied to a risk connected to health and information technology security. Risk analysis requires…

As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models (LLMs) offer significant potential in cybersecurity due to their advanced capabilities in text processing and…

Studying the robustness of Large Language Models (LLMs) to unsafe behaviors is an important topic of research today. Building safety classification models or guard models, which are fine-tuned models for input/output safety classification…

The literature and multiple experts point to many potential risks from large language models (LLMs), but there are still very few direct measurements of the actual harms posed. AI risk assessment has so far focused on measuring the models'…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and…

As language models (LMs) advance, interest is growing in applying them to high-stakes societal decisions, such as determining financing or housing eligibility. However, their potential for discrimination in such contexts raises ethical…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

Automated label generation for clusters of scientific documents is a common task in bibliometric workflows. Traditionally, labels were formed by concatenating distinguishing characteristics of a cluster's documents; while straightforward,…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Due to its general-purpose nature, Generative AI is applied in an ever-growing set of domains and tasks, leading to an expanding set of risks of harm impacting people, communities, society, and the environment. These risks may arise due to…

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

This paper introduces a standardized model card framework specifically designed for digital and web forensics. Building upon established model card methodologies and recent work on abstract models for digital forensic analysis, this paper…

Automated text generation has been applied broadly in many domains such as marketing and robotics, and used to create chatbots, product reviews and write poetry. The ability to synthesize text, however, presents many potential risks, while…