We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses
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.
Code (1)
Tasks
Dialogue GenerationLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling
Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving …
Language ModelingLanguage ModellingA Structured Clustering Approach for Inducing Media Narratives
Media narratives wield tremendous power in shaping public opinion, yet computational approaches struggle to capture the nuanced storytelling structures that communication theory emphasizes as central to how meaning is co…
HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents
Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions. Recursive contex…
Optimal Retirement Time and Consumption with the Variation in Habitual Persistence
In this paper,we study the individual's optimal retirement time and optimal consumption under habitual persistence. Because the individual feels equally satisfied with a lower habitual level and is more reluctant to chan…
SensitivityTowards Natural Language Story Understanding with Rich Logical Schemas
Generating {``}commonsense{'}{'} knowledge for intelligent understanding and reasoning is a difficult, long-standing problem, whose scale challenges the capacity of any approach driven primarily by human input. Furthermo…