Ability to penalize tokens that have already been used, encouraging the model to introduce new tokens.
AI/ML / Gen AI / Capabilities / DEV
Parameter Tuning - Presence Penalty
CCC.GenAI.CP13
Related Threats
| ID | Title | Description |
|---|---|---|
| CCC.GenAI.TH04 | Insecure / Unreliable Model Output | A GenAI model may generate content that is incorrect, misleading or harmful, such as convincing misinformation (hallucinations) or vulnerable or malicious code, due to its reliance on statistical patterns rather than factual understanding. Directly using this flawed output without validation can lead to system compromises, poor decision-making, and legal or reputational damage. |