| title | Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals |
|---|---|
| authors | Federico Torrielli, Peter Schneider-Kamp, Lukas Galke Poech |
| date | 2026-05-25 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.26045 |
| affiliation | AI Safety & Interpretability Lab |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty quantification (UQ) for the natural-language outputs of such activation oracles is so far understudied. Here, we investigate 6 different methods for estimating the confidence of activation oracles and evaluate how well-calibrated their confidence scores are. Our experiments on 6,000 samples per oracle (varying verbalizer and context prompts) reveal that bootstrap mode frequency is the best-calibrated method among those tested (ECE 5.7% vs. 25.5% for the answer-word log-probability on Qwen3-8B; 10.3% vs. 13.1% on Qwen3.6-27B), and that the log-prob baseline can serve as a fast triage signal at a fraction of the cost. Code and the patched trainer are available at https://github.com/federicotorrielli/probabilistic_activation_oracles. |
cite
@misc{torrielli2026confidence,
title={Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals},
author={Federico Torrielli and Peter Schneider-Kamp and Lukas Galke Poech},
year={2026},
eprint={2605.26045},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.26045}
}