RUNTIME ALIGNMENT OF LANGUAGE MODELS IN CONVERSATIONAL AI SYSTEMS AND APPLICATIONS

Systems and techniques are described related to providing dynamic, configurable, runtime model alignment-in the form of guardrails, in embodiments-for language models (such as LLMs) using a formal modeling language. In at least one embodiment, a dialog flow is determined based on a user input and ex...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: PARISIEN, Christopher Marc, COHEN, Jonathan Michael, DINU, Razvan, REBEDEA, Traian-Eugen
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Systems and techniques are described related to providing dynamic, configurable, runtime model alignment-in the form of guardrails, in embodiments-for language models (such as LLMs) using a formal modeling language. In at least one embodiment, a dialog flow is determined based on a user input and executed using a language model to generate an output. The dialog flow is specified in a formal modeling programming language and controls output of the language model.