Jev glossary
Evaluation & TrainingMode collapse
Mode dropping
Preference optimization narrowing a model's output distribution toward a favored style and away from other valid outputs.
- Category
- Evaluation & Training
- Also known as
- Mode collapse
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The primer illustrates mode dropping as the distribution of a base model compared with a narrowed, mode-dropped distribution after RLHF. The model learns to favor a particular style, such as instruction following, while reducing the probability of other possible outputs.
It is a milder version of mode collapse, the GAN failure mode where a generator produces the same kind of output repeatedly. For decision models the concern is the opposite of diversity: probabilities that no longer reflect the real chance of being right.
Tagstraininglimitations
Related terms
Definitions that connect to this one.
RLHFThe human-preference training method that turned pretrained models into chatbots, and the method TypeSafe deliberately did not use.Evaluation & TrainingCalibrationThe property that outcomes given a probability of 0.2 occur about 20% of the time, measured across many predictions.Answers & ConfidenceSycophancyThe tendency of preference-trained models to say what people want to hear, one of the reasons TypeSafe chose a calibration objective.Evaluation & Training
From the Jev directory
Directory entries that go deeper on this term.
Why TypeSafe trains decision models with RLCD instead of RLHF: calibrated probabilities where 0.2 outcomes happen about 20% of the time, and the case for machine-to-machine automation.
Jev Guides & ArticlesDocs#official#docs#evaluation
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.