ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps
Quick summary
arXiv:2609.11498v1 Announce Type: new Abstract: 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 hidden- state trajectory (every layer, every generated token) into a fixed $12 \times 32 \times 128$ tensor of temporal-statistic channels that preserves st
Key takeaways
- arXiv:2609.11498v1 Announce Type: new Abstract: 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 hidden- state trajectory (every layer, every generated token) into a fixed $12 \times 32 \times 128$ tensor of temporal-statistic channels that preserves st
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments