2 papers
cs.AI2026
ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps
Jacopo Dardini, Roberta Calegari
Practical uncertainty quantification (UQ) for large language models must decide, from a single generation, whether a specific answer should be trusted. Existing methods either samp…
cs.LG2026
Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap
Jacopo Dardini, Claudio Stanzione, Giordano Colò +1
Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluate…