Related papers: Aetheria: A multimodal interpretable content safet…
AI-driven speech-to-text (STT) documentation systems are increasingly adopted in clinical settings to reduce documentation burden and improve workflow efficiency. However, adoption has outpaced systematic evaluation of socio-technical risks…
Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…
The conceptual framework proposed in this paper centers on the development of a deliberative moral reasoning system - one designed to process complex moral situations by generating, filtering, and weighing normative arguments drawn from…
The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and…
Automatic question generation (AQG) for mathematics education remains an elusive goal for Intelligent Tutoring Systems and educators. While pre-trained transformer-based language models have significantly advanced natural language…
The deployment and use of AI systems should be both safe and broadly ethically acceptable. The principles-based ethics assurance argument pattern is one proposal in the AI ethics landscape that seeks to support and achieve that aim. The…
Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explainability, fairness, robustness, privacy, and sustainability mostly in isolation. We…
Generative AI systems are increasingly embedded in everyday life, yet empirical understanding of how psychological risk associated with AI use emerges, is experienced, and is regulated by users remains limited. We present a large-scale…
Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…
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…
We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation,…
Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…
The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible…
The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on.…
In the past decade, the deployment of deep learning (Artificial Intelligence (AI)) methods has become pervasive across a spectrum of real-world applications, often in safety-critical contexts. This comprehensive research article rigorously…
Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…
Significant digitalization of financial services in a short period of time has led to an urgent demand to have autonomous, transparent and real-time credit risk decision making systems. The traditional machine learning models are effective…
Content moderation is a widely used strategy to prevent the dissemination of irregular information on social media platforms. Despite extensive research on developing automated models to support decision-making in content moderation, there…
Given the societal impact of unsafe content generated by large language models (LLMs), ensuring that LLM services comply with safety standards is a crucial concern for LLM service providers. Common content moderation methods are limited by…
The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This…