Related papers: Evaluating the Effectiveness of OpenAI's Parental …
Generative Artificial Intelligence (GenAI) has become a central component of many development tools (e.g., GitHub Copilot) that support software practitioners across multiple programming tasks, including code completion, documentation, and…
Ensuring the safety of Generative AI requires a nuanced understanding of pluralistic viewpoints. In this paper, we introduce a novel data-driven approach for analyzing ordinal safety ratings in pluralistic settings. Specifically, we address…
AI systems crucially rely on human ratings, but these ratings are often aggregated, obscuring the inherent diversity of perspectives in real-world phenomenon. This is particularly concerning when evaluating the safety of generative AI,…
Blind and low vision (BLV) individuals use Generative AI (GenAI) tools to interpret and manage visual content in their daily lives. While such tools can enhance the accessibility of visual content and so enable greater user independence,…
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…
This research article explores the potential of Artificial Intelligence (AI) and Chat Generative Pre-trained Transformers (ChatGPT) in revolutionizing the landscape of parental support and child care. With the advancement of generative AI,…
Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…
As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural contexts. To examine how current model safeguards hold up in such settings, participants from…
Undoubtedly, the evolution of Generative AI (GenAI) models has been the highlight of digital transformation in the year 2022. As the different GenAI models like ChatGPT and Google Bard continue to foster their complexity and capability,…
Domain fine-tuning is a common path to deploy small instruction-tuned language models as customer-support assistants, yet its effects on safety-aligned behavior and privacy are not well understood. In real deployments, such assistants…
As generative AI (GenAI) tools are increasingly used as informal tutors for mathematics learning, future systems may become more proactive and process-aware in deciding when and how to offer support. Yet such support raises an important…
AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation…
Artificial intelligence systems are now deployed at scale across sectors, accompanied by a growing number of real-world incidents ranging from misinformation and cybercrime to autonomous-system failures. Databases of AI incidents index…
As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a comprehensive evaluation of 14 open-source safety guard models on a curated benchmark of…
The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present…
Collecting data on sensitive topics remains challenging in HCI, as participants often withhold information due to privacy concerns and social desirability bias. While chatbots' perceived anonymity may reduce these barriers, research…
We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM…
AI coding assistants are now central to professional software development, yet their impact on how developers think about and practice security remains poorly understood. While prior work has documented vulnerability rates in AI-generated…
Generative AI (GAI) is reshaping the way young users engage with technology. This study introduces a taxonomy of risks associated with youth-GAI interactions, derived from an analysis of 344 chat transcripts between youth and GAI chatbots,…
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…