Brief
AWS offers model-agnostic PII detector that adapts without retraining
AWS has described a configurable, model-agnostic detector that turns any large language model on Amazon Bedrock into a PII detector. The entities to detect live in a prompt rather than in code, so one detector adapts to new entity types without retraining.
The detector is configurable and model-agnostic, turning any large language model on Amazon Bedrock into a PII detector. Because the entities to detect live in a prompt rather than in code, one detector can adapt to new entity types without retraining. The source states it outperforms an off-the-shelf tool across five public corpora and nine LLM-based detectors. For teams using AI for everyday work, this means PII detection can be updated by changing a prompt, not by rebuilding a model.
Source details and supporting facts
Each line is stated by the page named above it.
Stated by aws.amazon.com
- A configurable, model-agnostic detector turns any large language model on Amazon Bedrock into a PII detector.
- The entities to detect live in a prompt rather than in code, so one detector adapts to new entity types without retraining.
- It outperforms an off-the-shelf tool across five public corpora and nine LLM-based detectors.
Sources
- AWS Machine Learning BlogText stored 15 September 2026
How this story was checked. Written from the 1 page listed above, stored 15 September 2026; claims checked against that stored text on 15 September 2026.
What that means
- 3 of 3 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
- Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
- The check reads stored text only: no claim rests on a fresh look that did not happen.
- Where the reporting was silent, the text says so instead of filling the gap.