🛰️ Daily AI Frontier
‹ back to 2026-09-12

ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps

Research LLMs & Foundation Models

Ranking

Overall 79
Content 95
Popularity 42

Observed public metrics from 1 member.

Representative image for ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps

Merged summary

TL;DR - ActMap estimates an LLM answer’s correctness from a single generation by compactly encoding hidden-state activity across every layer and generated token. It enables low-overhead uncertainty scoring for abstention, routing, and selective verification.

  • Compresses generation-time activations into a fixed 12 Ă— 32 Ă— 128 tensor occupying 96 KiB, with no measurable capture overhead.
  • A lightweight classifier predicts correctness in under a millisecond; comparable MLP results suggest the representation, rather than classifier architecture, drives performance.
  • Across QA, math, and summarization factuality tasks with three instruction-tuned 7–8B models, ActMap outperformed sampling, token-probability, attention, and embedding baselines.
  • It matched the mean AUROC of ACT-ViT while using activation tensors 67Ă— smaller and achieved lower calibration error on 10 of 12 evaluated pairs.

Sources (1)

ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps

arXiv cs.AI Jacopo Dardini, Roberta Calegari 2026-09-10 arXiv:2609.11498
Public signals Hugging Face upvotes 0
Providers: Hugging Face · Upvotes 0 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-25 14:20:33.355110 UTC

TL;DR - ActMap estimates an LLM answer’s correctness from a single generation by compactly encoding hidden-state activity across every layer and generated token. It enables low-overhead uncertainty scoring for abstention, routing, and selective verification.

  • Compresses generation-time activations into a fixed 12 Ă— 32 Ă— 128 tensor occupying 96 KiB, with no measurable capture overhead.
  • A lightweight classifier predicts correctness in under a millisecond; comparable MLP results suggest the representation, rather than classifier architecture, drives performance.
  • Across QA, math, and summarization factuality tasks with three instruction-tuned 7–8B models, ActMap outperformed sampling, token-probability, attention, and embedding baselines.
  • It matched the mean AUROC of ACT-ViT while using activation tensors 67Ă— smaller and achieved lower calibration error on 10 of 12 evaluated pairs.
item →