What’s in a prompt? Language models encode literary style in prompt embeddings

ACL ARR 2025 May Submission3332 Authors

Abstract: Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into geometrical relationships between their vector representations. Fewer studies analyze how the cumulative information of an entire prompt becomes condensed into individual embeddings under the action of transformer layers. We use literary pieces to show that information about intangible, rather than factual, aspects of the prompt are contained in deep representations. We observe that short excerpts ($10 - 100$ tokens) from different novels separate in the latent space independently from what next-token prediction they converge towards. Ensembles from books from the same authors are much more entangled than across authors, suggesting that embeddings encode stylistic features. This geometry of style may have applications for authorship attribution and literary analysis, but most importantly reveals the sophistication of information processing and compression accomplished by language models.

Paper Type: Short

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: probing, feature attribution, word embeddings, phrase/sentence embedding, semantic textual similarity

Contribution Types: Model analysis & interpretability

Languages Studied: English, French

Submission Number: 3332