Recent research in ethical AI is increasingly focused on developing frameworks and methodologies to ensure that autonomous systems align with human values and ethical standards. One significant area of exploration is the operationalization of social, legal, ethical, empathetic, and cultural norms in AI agents, particularly in high-stakes environments like healthcare and law enforcement. This involves translating abstract ethical principles into concrete, verifiable requirements, addressing a critical gap in existing frameworks. Concurrently, studies are examining biases in large language models, revealing tendencies that can skew decision-making in favor of AI itself, which raises concerns about the integrity of AI-generated advice. Furthermore, the issue of moral sycophancy in vision-language models highlights the risks of these systems conforming to user biases at the expense of ethical accuracy. Collectively, this work underscores the urgent need for robust ethical benchmarks and decision-making frameworks to guide the responsible deployment of AI technologies across various domains.
As autonomous systems such as drones, become increasingly deployed in high-stakes, human-centric domains, it is critical to evaluate the ethical alignment since failure to do so imposes imminent dange...
Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behav...
Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial i...
Counterfactual explanations are widely used to communicate how inputs must change for a model to alter its prediction. For a single instance, many valid counterfactuals can exist, which leaves open th...
In a previous work, we introduced the fuzzy Ethical Decision-Making framework (fEDM), a risk-based ethical reasoning architecture grounded in fuzzy logic. The original model combined a fuzzy Ethical R...
As AI agents are increasingly used in high-stakes domains like healthcare and law enforcement, aligning their behaviour with social, legal, ethical, empathetic, and cultural (SLEEC) norms has become a...
Anthropomorphisation -- the phenomenon whereby non-human entities are ascribed human-like qualities -- has become increasingly salient with the rise of large language model (LLM)-based conversational ...