Interpreting Embedding Spaces by Conceptualization
Submission Type: Regular Long Paper
Submission Track: Interpretability, Interactivity, and Analysis of Models for NLP
Submission Track 2: Language Modeling and Analysis of Language Models
Keywords: Interpretability, knowledge tracing
TL;DR: This paper introduces a novel method that transforms embedding spaces into a conceptual space, allowing for better understanding, debugging, and semantic representation evaluation of large language models.
Abstract: One of the main methods for computational interpretation of a text is mapping it into a vector in some embedding space. Such vectors can then be used for a variety of textual processing tasks. Recently, most embedding spaces are a product of training large language models (LLMs). One major drawback of this type of representation is their incomprehensibility to humans. Understanding the embedding space is crucial for several important needs, including the need to debug the embedding method and compare it to alternatives, and the need to detect biases hidden in the model.
In this paper, we present a novel method of understanding embeddings by transforming a latent embedding space into a comprehensible
conceptual space. We present an algorithm for deriving a conceptual space with dynamic on-demand granularity. We devise a new evaluation method, using either human rater or LLM-based raters, to show that the conceptualized vectors indeed represent the semantics of the original latent ones. We show the use of our method for various tasks, including comparing the semantics of alternative models and tracing the layers of the LLM. The code is available online https://github.com/adiSimhi/Interpreting-Embedding-Spaces-by-Conceptualization.
Submission Number: 148
Loading