Calibration

A calibrated model's 70 percent means it is right 70 percent of the time. Most LLMs are not calibrated. Here is what that costs you.

40 min · Reviewed 2026

Probabilities That Mean Something

A calibrated classifier is one whose probability estimates match real frequencies. If it says 70 percent across a batch of predictions, 70 percent of those should be correct. That is an uncommon property in modern LLMs.

The reliability diagram

To check calibration, bin predictions by confidence (0-10 percent, 10-20 percent, ). For each bin, plot average confidence vs empirical accuracy. A perfectly calibrated model hugs the diagonal. Overconfidence bends the line below; underconfidence bends it above.

Perfect calibration: Accuracy 1.0 | * 0.8 | * 0.6 | * 0.4 | * 0.0 *--------- Confidence 0.0 0.6 1.0 Real models often look like: Accuracy 1.0 | * 0.8 | * * (overconfident) 0.6 | * 0.4 | * 0.0 *--------- Confidence too high relative to truth.Reliability diagram: where the model thinks it is vs where it actually is

Expected Calibration Error (ECE)

ECE sums the gap between confidence and accuracy across bins, weighted by bin size. Lower is better. A well-calibrated model has ECE below 0.05. A raw out-of-the-box LLM often sits at 0.15 or higher.

Why LLMs miscalibrate

RLHF training rewards confident responses — hedging sounds weak
Text never contains explicit probability labels to learn from
The Softmax output is sensitive to fine-tuning choices
In-context examples can push confidence up or down arbitrarily

Fixes that help

Temperature scaling: post-hoc sharpen or flatten the probability curve
Prompting for probabilities then calibrating offline
Ensemble over samples (semantic entropy)
Few-shot examples that demonstrate appropriate uncertainty

Modern neural networks are not calibrated — a phenomenon that has worsened as accuracy improved.
— Guo et al., On Calibration of Modern Neural Networks (2017)

The big idea: a confident answer is not a correct answer. Calibration is the bridge between the two.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-creators-calibration

What is the main idea of "Calibration"?
1. A calibrated model's 70 percent means it is right 70 percent of the time. Most LLMs are not calibrated. Here is what that costs you.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Calibration"?
1. reliability diagram
2. calibration
3. ECE
4. overconfidence
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. RLHF training rewards confident responses — hedging sounds weak
4. Treat the AI output as automatically correct
What should a careful learner remember about "Overconfidence is the default"?
1. Use AI to draft or organize ideas about calibration, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about calibration be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about calibration.
Which action would help you apply "Calibration" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Text never contains explicit probability labels to learn from

← Back to interactive lesson

Tendril · Creators · AI Foundations

Calibration

A calibrated model's 70 percent means it is right 70 percent of the time. Most LLMs are not calibrated. Here is what that costs you.

40 min · Reviewed 2026

Probabilities That Mean Something

The reliability diagram

Perfect calibration: Accuracy 1.0 | * 0.8 | * 0.6 | * 0.4 | * 0.0 *--------- Confidence 0.0 0.6 1.0 Real models often look like: Accuracy 1.0 | * 0.8 | * * (overconfident) 0.6 | * 0.4 | * 0.0 *--------- Confidence too high relative to truth.Reliability diagram: where the model thinks it is vs where it actually is

Expected Calibration Error (ECE)

ECE sums the gap between confidence and accuracy across bins, weighted by bin size. Lower is better. A well-calibrated model has ECE below 0.05. A raw out-of-the-box LLM often sits at 0.15 or higher.

Why LLMs miscalibrate

RLHF training rewards confident responses — hedging sounds weak
Text never contains explicit probability labels to learn from
The Softmax output is sensitive to fine-tuning choices
In-context examples can push confidence up or down arbitrarily

Fixes that help

Temperature scaling: post-hoc sharpen or flatten the probability curve
Prompting for probabilities then calibrating offline
Ensemble over samples (semantic entropy)
Few-shot examples that demonstrate appropriate uncertainty

Modern neural networks are not calibrated — a phenomenon that has worsened as accuracy improved.
— Guo et al., On Calibration of Modern Neural Networks (2017)

The big idea: a confident answer is not a correct answer. Calibration is the bridge between the two.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-creators-calibration

What is the main idea of "Calibration"?
1. A calibrated model's 70 percent means it is right 70 percent of the time. Most LLMs are not calibrated. Here is what that costs you.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Calibration"?
1. reliability diagram
2. calibration
3. ECE
4. overconfidence
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. RLHF training rewards confident responses — hedging sounds weak
4. Treat the AI output as automatically correct
What should a careful learner remember about "Overconfidence is the default"?
1. Use AI to draft or organize ideas about calibration, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about calibration be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about calibration.
Which action would help you apply "Calibration" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Text never contains explicit probability labels to learn from

← Back to interactive lesson