Reliability
Behavioural Consistency
Techniques that check or enforce that a system keeps behaving as specified across scenarios, not just scoring well.
4 techniques
4 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Monotonicity Constraints | Algorithmic | Architecture/neural Networks Architecture/probabilistic/gaussian Processes +3 | Tabular | Monotonicity constraints require a model's prediction to move only one way as a chosen input rises, with the other... | ||
| Agent Goal Misalignment Testing | Testing | Architecture/model Agnostic Architecture/neural Networks/transformer/llm +3 | Text | Agent goal misalignment testing checks whether an AI agent takes unsanctioned means to reach a goal it has been given.... | ||
| Constitutional AI Evaluation | Testing | Architecture/neural Networks/transformer/llm Requirements/white Box +1 | Text | Constitutional AI evaluation checks whether a language model follows the written principles, or 'constitution', that it... | ||
| Reward Hacking Detection | Testing | Architecture/model Agnostic Architecture/neural Networks/transformer/llm +2 | Any | Reward hacking is when an agent trained to maximise a proxy reward (a score that only approximates what its designers... |
Rows per page
Page 1 of 1