Related papers: Anticipating Safety Issues in E2E Conversational A…
Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achieving pre-defined targets or fulfilling…
Artificial intelligence (AI) developers are increasingly building language models with warm and empathetic personas that millions of people now use for advice, therapy, and companionship. Here, we show how this creates a significant…
This work explores the impact of moderation on users' enjoyment of conversational AI systems. While recent advancements in Large Language Models (LLMs) have led to highly capable conversational AIs that are increasingly deployed in…
Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Artificial intelligence chatbots have achieved unprecedented adoption, with millions now using these systems for emotional support and companionship in contexts of widespread social isolation and capacity-constrained mental health services.…
The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance.…
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…
Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to reason step-by-step and inference-time enhancements have…
Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better…
Designing a driving policy for autonomous vehicles is a difficult task. Recent studies suggested an end-toend (E2E) training of a policy to predict car actuators directly from raw sensory inputs. It is appealing due to the ease of labeled…
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…
End-to-end neural TTS has achieved superior performance on reading style speech synthesis. However, it's still a challenge to build a high-quality conversational TTS due to the limitations of the corpus and modeling capability. This study…
Like many research communities, ethnomethodologists and conversation analysts have begun to get caught up -- yet again -- in the pervasive spectacle of surging interests in Artificial Intelligence (AI). Inspired by discussions amongst a…
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…
Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…
As the capabilities of generative language models continue to advance, the implications of biases ingrained within these models have garnered increasing attention from researchers, practitioners, and the broader public. This article…
Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields, ranging from speech processing, image classification to drug discovery. This is driven by the explosive growth of data, advances in machine…