Easy Safety Question 57 of 223

What is PII and why does it matter for LLMs?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

Train 70%Val 15%Test 15%

Fit on train, tune on val, report on test once.

PII is personally identifiable information such as names, emails, and IDs.

LLMs use tokens (not full words) because it helps them:

Safety questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

Before the model can read a sentence, it goes through these steps:

1
PII is personally identifiable
information such as names, emails, and IDs.
2
Sending it to a
model can leak it in logs, training, or later answers.
3
Redact, minimize, and apply
retention rules before you call an LLM.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Sending it to a model can leak it in logs, training, or later answers.”

Tokenized output

Sendingittoamodelcan

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

PII is personally identifiable information such as names, emails, and IDs. Sending it to a model can leak it in logs, training, or later answers.