ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps
Practical uncertainty quantification (UQ) for large language models must decide, from a single generation, whether a specific answer should be trusted. Existing methods either sample multiple generations, read only output-token probabilities, or reduce the model's internal computation to a single hidden state. We introduce ActMap, a white-box representation that compresses the generation-time…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
