We Are What We Repeatedly Do: Inducing and Deploying Habitual Schemas in Persona-Based Responses
Submission Type: Regular Long Paper
Submission Track: Natural Language Generation
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: Dialogue, Response, Generation, Persona, Schema, LLM
TL;DR: We propose and evaluate a method for generating interesting persona-based responses using LLMs by first inducing symbolic event schemas.
Abstract: Many practical applications of dialogue technology require the generation of responses according to a particular developer-specified persona. While a variety of personas can be elicited from recent large language models, the opaqueness and unpredictability of these models make it desirable to be able to specify personas in an explicit form. In previous work, personas have typically been represented as sets of one-off pieces of self-knowledge that are retrieved by the dialogue system for use in generation. However, in realistic human conversations, personas are often revealed through story-like narratives that involve rich habitual knowledge -- knowledge about kinds of events that an agent often participates in (e.g., work activities, hobbies, sporting activities, favorite entertainments, etc.), including typical goals, sub-events, preconditions, and postconditions of those events. We capture such habitual knowledge using an explicit schema representation, and propose an approach to dialogue generation that retrieves relevant schemas to condition a large language model to generate persona-based responses. Furthermore, we demonstrate a method for bootstrapping the creation of such schemas by first generating generic passages from a set of simple facts, and then inducing schemas from the generated passages.
Submission Number: 2142
Loading