Related papers: RubRIX: Rubric-Driven Risk Mitigation in Caregiver…
Psychological consultation is essential for improving mental health and well-being, yet challenges such as the shortage of qualified professionals and scalability issues limit its accessibility. To address these challenges, we explore the…
The AI landscape demands a broad set of legal, ethical, and societal considerations to be accounted for in order to develop ethical AI (eAI) solutions which sustain human values and rights. Currently, a variety of guidelines and a handful…
Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and automated data analysis. Current approaches to dataset risk analysis are limited to manual…
Current AI safety frameworks, which often treat harmfulness as binary, lack the flexibility to handle borderline cases where humans meaningfully disagree. To build more pluralistic systems, it is essential to move beyond consensus and…
Evaluating UX in the context of AI's complexity, unpredictability, and generative nature presents unique challenges. How can we support HCI researchers to create comprehensive UX evaluation plans? In this paper, we introduce EvAlignUX, a…
Multi-dimensional rubric-based dialogue evaluation is widely used to assess conversational AI, yet its criterion validity -- whether quality scores are associated with the downstream outcomes they are meant to serve -- remains largely…
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…
Conversational AI systems can engage in unsafe behaviour when handling users' medical queries that can have severe consequences and could even lead to deaths. Systems therefore need to be capable of both recognising the seriousness of…
The emergence of large language models (LLMs) has unlocked boundless possibilities, along with significant challenges. In response, we developed a mental health support chatbot designed to augment professional healthcare, with a strong…
Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…
As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…
Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks--fail to capture the clinically critical dimensions of…
Tensions between AI Safety (AIS) and AI Ethics (AIE) have increasingly surfaced in AI governance and public debates about AI, leading to what we term the "responsible AI divides". We introduce a model that categorizes four modes of…
The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…
Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based…
Interest in the concept of AI-driven harmful manipulation is growing, yet current approaches to evaluating it are limited. This paper introduces a framework for evaluating harmful AI manipulation via context-specific human-AI interaction…
LLM-based agents can complete tasks correctly yet still frustrate users through poor interaction patterns, such as excessive confirmations, opaque reasoning, or misaligned pacing. Current benchmarks evaluate task accuracy but overlook how…
Public attitudes toward artificial intelligence (AI) and driving safety are typically studied in isolation using variable-centered methods that assume population homogeneity, yet risk perception theory predicts that these evaluations covary…
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…
Large Language Models (LLMs) exhibit systematic risk-taking behaviors analogous to those observed in gambling psychology, including overconfidence bias, loss-chasing tendencies, and probability misjudgment. Drawing from behavioral economics…