Evidence record 5963 · automatically gathered

Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?

Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the target behavior, so apparent gains from white-box tools may reflect elicitation rather than internal signal; we call this the elicitation confounder. We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis: models are train

Record details

Published: 13 April 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Transparency
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (13 April 2026), “Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?,” evidence record 5963, https://ethics.ai/record/5963 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.