Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirementsby Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda,…
Mentor-KD: Making Small Language Models Better Multi-step Reasonersby Hojae Lee, Junho Kim, SangKeun LeeFirst submitted…
Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspectiveby Bo Ni, Yu Wang, Lu Cheng,…
Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposalby…
Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulationsby Henry Gasztowtt, Benjamin Smith, Vincent…
Optimizing Vital Sign Monitoring in Resource-Constrained Maternal Care: An RL-Based Restless Bandit Approachby Niclas Boehmer,…
The GUS Framework: Benchmarking Social Bias Classification with Discriminative (Encoder-Only) and Generative (Decoder-Only) Language Modelsby…
KV Prediction for Improved Time to First Tokenby Maxwell Horton, Qingqing Cao, Chenfan Sun, Yanzi…
The Effects of Hallucinations in Synthetic Training Data for Relation Extractionby Steven Rogulsky, Nicholas Popovic,…
AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuningby Muhammad Awais, Ali Husain Salem Abdulla Alharthi,…