10 papers
Direct Causation in International Humanitarian Law and the Challenge of AI-Mediated Civilian Cyber Operations
Alice Saito, Harold Godsoe, Phan Xuan Tan
International humanitarian law protects civilians from direct attack unless and for such time as they take direct part in hostilities, with the ICRC's 2009 Interpretive Guidance op…
Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies
Serena A. Hoffstedde, Machiko Hirota, Akshara Nadayanur Sathis Kanna +4
Large language models (LLMs) are increasingly deployed in hiring workflows, yet most research on gender bias in LLM hiring decisions has focused on English-language, Western-format…
Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure
Ujwal Kumar, Arth Singh, Hershraj Niranjani +5
Frontier LLM agents engage in blackmail, sabotage, and document leaks under goal conflicts in agentic settings, exposing limitations of alignment methods built around single-agent…
Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
Hershraj Niranjani, Ujwal Kumar, Phan Xuan Tan
Multi-agent AI systems need behavioral constitutions, but it is unresolved whether such rules should emerge internally through agent self-governance or be discovered externally thr…
Evolving Interpretable Constitutions for Multi-Agent Coordination
Ujwal Kumar, Alice Saito, Hershraj Niranjani +2
Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We…
Memorization Control in Diffusion Models from Denoising-centric Perspective
Thuy Phuong Vu, Mai Viet Hoang Do, Minhhuy Le +2
Controlling memorization in diffusion models is critical for applications that require generated data to closely match the training distribution. Existing approaches mainly focus o…