On Semantic Cognition, Inductive Generalization, and Language Models
This work addresses the challenge of interpreting semantic cognition in AI models for researchers in cognitive science and machine learning, but it appears incremental as it applies existing cognitive theories to language models without claiming major breakthroughs.
The research tackles the problem of understanding semantic knowledge in language models by proposing a framework inspired by human inductive reasoning, aiming to analyze how these models generalize from new information about concepts and properties.
My doctoral research focuses on understanding semantic knowledge in neural network models trained solely to predict natural language (referred to as language models, or LMs), by drawing on insights from the study of concepts and categories grounded in cognitive science. I propose a framework inspired by 'inductive reasoning,' a phenomenon that sheds light on how humans utilize background knowledge to make inductive leaps and generalize from new pieces of information about concepts and their properties. Drawing from experiments that study inductive reasoning, I propose to analyze semantic inductive generalization in LMs using phenomena observed in human-induction literature, investigate inductive behavior on tasks such as implicit reasoning and emergent feature recognition, and analyze and relate induction dynamics to the learned conceptual representation space.