Related papers: Constitutional AI: Harmlessness from AI Feedback

One of the fundamental quests of AI is to produce agents that coordinate well with humans. This problem is challenging, especially in domains that lack high quality human behavioral data, because multi-agent reinforcement learning (RL)…

Software testing remains critical for ensuring reliability, yet traditional approaches are slow, costly, and prone to gaps in coverage. This paper presents an AI-driven framework that automates test case generation and validation using…

Current AI systems minimize risk by enforcing ideological neutrality, yet this may introduce automation bias by suppressing cognitive engagement in human decision-making. We conducted randomized trials with 2,500 participants to test…

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neurosymbolic…

Real-world reinforcement learning (RL) offers a promising approach to training precise and dexterous robotic manipulation policies in an online manner, enabling robots to learn from their own experience while gradually reducing human labor.…

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

In this demo, we present ConsciousControlFlow(CCF), a prototype system to demonstrate conscious Artificial Intelligence (AI). The system is based on the computational model for consciousness and the hierarchy of needs. CCF supports typical…

How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. The AI assistance problem concerns designing an AI agent that…

We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A)…

A framework is proposed that seeks to identify and establish a set of robust autonomous levels articulating the realm of Artificial Intelligence and Legal Reasoning (AILR). Doing so provides a sound and parsimonious basis for being able to…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

In this paper, we argue that anthropomorphized technology, designed to simulate emotional realism, are not neutral tools but cognitive infrastructures that manipulate user trust and behaviour. This reinforces the logic of surveillance…

AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true…

Imitation learning attracts much attention for its ability to allow robots to quickly learn human manipulation skills through demonstrations. However, in the real world, human demonstrations often exhibit random behavior that is not…

Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically apply constrained optimization techniques to ML training,…

Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment -- e.g. game score, completion time, etc. -- in order to learn the optimal strategy for task performance. However, Human-AI…

Advanced AI systems are now being used in AI governance. Practitioners will likely delegate an increasing number of tasks to them as they improve and governance becomes harder. However, using AI for governance risks serious harms because…

Human interventions are a common source of data in autonomous systems during testing. These interventions provide an important signal about where the current policy needs improvement, but are often noisy and incomplete. We define Robust…

This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…