Extracting Conceptual Spaces from LLMs Using Prototype Embeddings

ACL ARR 2025 May Submission6113 Authors

Abstract: Conceptual spaces represent entities and concepts using cognitively meaningful dimensions, typically referring to perceptual features. Such representations are widely used in cognitive science and have the potential to serve as a cornerstone for explainable AI. Unfortunately, they have proven notoriously difficult to learn, although recent LLMs appear to capture the required perceptual features to a remarkable extent. Nonetheless, practical methods for extracting the corresponding conceptual spaces are currently still lacking. While various methods exist for extracting embeddings from LLMs, extracting conceptual spaces also requires us to encode the underlying features. In this paper, we propose a strategy in which features (e.g. sweetness) are encoded by embedding the description of a corresponding prototype (e.g. a very sweet food). To improve this strategy, we fine-tune the LLM to align the prototype embeddings with the corresponding conceptual space dimensions. Our empirical analysis finds this approach to be highly effective.

Paper Type: Long

Research Area: Semantics: Lexical and Sentence-Level

Research Area Keywords: word embeddings, fine-tuning, concept explanations

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models

Languages Studied: English

Keywords: Word embeddings, Analysis of Models for NLP, Fine-tuning, Concept Explanations

Submission Number: 6113