#Ethical AI

Articles (10)

• 🇺🇸 When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making — 20/03/2026 [USA]

  arXiv:2603.18530v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characteri...

  Related: #AI Bias
• 🇺🇸 VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models — 20/03/2026 [USA]

  arXiv:2603.18113v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human valu...

  Related: #AI Alignment
• 🇺🇸 Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences — 17/03/2026 [USA]

  arXiv:2603.14531v1 Announce Type: new Abstract: Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safet...

  Related: #AI Safety
• 🇺🇸 COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics — 13/03/2026 [USA]

  arXiv:2603.11277v1 Announce Type: new Abstract: The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental susta...

  Related: #AI Governance
• 🇺🇸 Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs — 11/03/2026 [USA]

  arXiv:2603.09434v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed across diverse real-world applications and user communities. As such, it is crucial that these...

  Related: #AI Bias
• 🇺🇸 "Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior — 10/03/2026 [USA]

  arXiv:2603.06816v1 Announce Type: cross Abstract: The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities i...

  Related: #AI Safety
• 🇺🇸 Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure — 06/03/2026 [USA]

  arXiv:2603.05028v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to...

  Related: #AI Safety
• 🇺🇸 GPT-5.4 Thinking System Card — 05/03/2026 [USA] Related: #AI Transparency
• 🇺🇸 From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness — 16/02/2026 [USA]

  arXiv:2602.12285v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While ...

  Related: #AI Bias, #Autonomous Agents
• 🇺🇸 Ten years — 11/12/2025 [USA]

  OpenAI reflects on ten years of progress, from early research breakthroughs to widely used AI systems that reshaped what’s possible. We share lessons from the past decade and why we remain optimistic ...

  Related: #AI Development, #Technological Progress, #AGI Research