Learning Interpretable Style Embeddings via Prompting LLMs

Ajay Patel, Delip Rao, Ansh Kothary, Kathleen McKeown, Chris Callison-Burch

Submission Type: Regular Long Paper

Submission Track: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Submission Track 2: Interpretability, Interactivity, and Analysis of Models for NLP

Keywords: style, stylometry, representation learning, embeddings, vectors, interpretability, prompting, llm

TL;DR: In this work, we train interpretable style embedding models using large language models and prompting.

Abstract: Style representation learning builds content-independent representations of author style in text. To date, no large dataset of texts with stylometric annotations on a wide range of style dimensions has been compiled, perhaps because the linguistic expertise to perform such annotation would be prohibitively expensive. Therefore, current style representation approaches make use of unsupervised neural methods to disentangle style from content to create style vectors. These approaches, however, result in uninterpretable representations, complicating their usage in downstream applications like authorship attribution where auditing and explainability is critical. In this work, we use prompting to perform stylometry on a large number of texts to generate a synthetic stylometry dataset. We use this synthetic data to then train human-interpretable style representations we call LISA embeddings. We release our synthetic dataset (StyleGenome) and our interpretable style embedding model (LISA) as resources.

Submission Number: 414