Weakly Supervised Hallucination Detection in Transformers
Discover a novel weak supervision method to distill hallucination signals into transformer models for efficient, internal hallucination detection without e...
Predicting Container Service Needs to Cut Unproductive Moves
Improve container terminal efficiency by predicting service requirements and dwell times using advanced machine learning models.
Language Models’ Blind Refusal to Break Unjust Rules
Study reveals language models often refuse to bypass unjust or absurd rules, highlighting limits in AI moral reasoning and safety protocols.
High-Precision Shogi State-Space Estimation via Monte Carlo
Discover a precise Monte Carlo method estimating Shogi's state-space complexity at 6.55×10^68 positions, advancing AI and game theory research.
Multi-Stage Validation for Trustworthy Clinical Info Extraction
Discover a multi-stage validation framework enhancing large-scale clinical info extraction using LLMs for reliable, scalable healthcare data analysis.