An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models

arXiv:2404.03028v1 Announce Type: new
Abstract: Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small number of examples; in instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description before making predictions. Each of these procedures may be thought of as invoking a different form …

abstract arxiv cs.cl examples few-shot inductive inference language language models large language large language models learn lms loop modern natural natural language prompting small tasks type