Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces
This addresses the limitation of narrow domain applications in conceptual spaces for researchers in cognitive science and AI, but it is incremental as it builds on existing LLM capabilities.
The paper tackled the problem of learning conceptual spaces, a cognitive-linguistic framework for representing concepts, by exploring the potential of Large Language Models (LLMs) for this task, finding that fine-tuned BERT models can match or outperform GPT-3 despite being much smaller.
The theory of Conceptual Spaces is an influential cognitive-linguistic framework for representing the meaning of concepts. Conceptual spaces are constructed from a set of quality dimensions, which essentially correspond to primitive perceptual features (e.g. hue or size). These quality dimensions are usually learned from human judgements, which means that applications of conceptual spaces tend to be limited to narrow domains (e.g. modelling colour or taste). Encouraged by recent findings about the ability of Large Language Models (LLMs) to learn perceptually grounded representations, we explore the potential of such models for learning conceptual spaces. Our experiments show that LLMs can indeed be used for learning meaningful representations to some extent. However, we also find that fine-tuned models of the BERT family are able to match or even outperform the largest GPT-3 model, despite being 2 to 3 orders of magnitude smaller.