Papers by Lenhart Schubert
We Are What We Repeatedly Do: Inducing and Deploying Habitual Schemas in Persona-Based Responses (2023.emnlp-main)
Copied to clipboard
| Challenge: | a variety of personas can be elicited from large language models, but they are opaque and unpredictable. |
| Approach: | They propose an approach to dialogue generation that retrieves relevant schemas to condition a large language model to generate persona-based responses. |
| Outcome: | The proposed method captures habitual knowledge and generates persona-based responses from a large language model. |
Mining Logical Event Schemas From Pre-Trained Language Models (2022.acl-srw)
Copied to clipboard
| Challenge: | a pre-trained language model is induced into acting as a distribution over stories, a new system is proposed . NESL is a neural event schema learning system that combines large language models, FrameNet parsing, and simple behavioral schemas to bootstrap the learning process. |
| Approach: | They propose a neural event schema learning system that bootstraps the learning process by parsing pre-trained language models into simple behavioral schemas. |
| Outcome: | The proposed system combines large language models, a powerful logical representation of language, and simple behavioral schemas to bootstrap the learning process. |