Concern 65 · Working draft · editorial review in progress
Prompt-based extraction
Prompt-based extraction uses interactions with a model to try to recover material it retained from training.
Understanding the concern
The concern is that ordinary-looking access to a chatbot can sometimes expose more than general knowledge. Research has demonstrated training-text recovery in particular models, but success depends on the model, material, and testing conditions.
A refusal to one question does not prove that memorized material cannot surface elsewhere. Conversely, a fluent completion is not automatically recovered data. Developers need controlled privacy tests and evidence that matches the claim being made.
An example
A person who remembers a passage may reveal more when given its beginning than when asked a broad question about the subject.
Illustrative unless identified as a documented case.
Words in plain English
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Training
- The process of using examples to shape how an AI model behaves. Learning patterns from material does not establish that the material is true or fair.
- Prompt
- The instructions or information given to an AI to guide its response.
Evidence and its limits
Provides evidence of query-based training-data recovery; this guide intentionally omits attack instructions.
Carlini and colleagues · USENIX Security 2021 · Research study
Extracting Training Data from Large Language Models ↗ (opens in a new tab)Demonstrates training-text recovery in tested models, including public identifying details; not every output resembling personal data is a verified leak.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
How was potential recovery tested, and were claimed matches checked against actual source material?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Justice
Justice means fair treatment, fair procedures, and attention to who receives benefits and burdens. It asks whether people with less power can be heard and seek repair.
Look at outcomes across different groups and individual cases. Provide a usable way to challenge decisions and correct harm. Equal wording in a policy does not guarantee equal treatment in practice.
Ask together: Who benefits, who bears the cost, and who can challenge the decision?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.