Rater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v1 Announce Type: new Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels…
Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
arXiv:2510.12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the…
Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
arXiv:2604.06742v2 Announce Type: replace-cross Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift towards intent-driven software…
Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research
arXiv:2512.03054v3 Announce Type: replace-cross Abstract: Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions…
Perception-Aligned AI Outputs: End-to-End Visual Prediction for Uncertainty Communication in Clinical Decision-Making
arXiv:2205.04599v2 Announce Type: replace-cross Abstract: Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods…
OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
arXiv:2607.08423v2 Announce Type: replace Abstract: The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized…
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
arXiv:2607.15095v2 Announce Type: replace-cross Abstract: The formation of political coalitions is a complex negotiation driven by both concrete policy objectives…
A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance
arXiv:2607.16130v1 Announce Type: cross Abstract: AI governance increasingly requires judgments about whether an AI system remains adequately trustworthy over time,…
ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning
arXiv:2607.16131v1 Announce Type: cross Abstract: Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
arXiv:2607.15263v2 Announce Type: replace-cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit…