paper-with-me

홈 › Papers

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models

2025-01-01 · Benjamin Icard, Evangelia Zve, Lila Sainero, Alice Breton, Jean-Gabriel Ganascia

This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of writing style in shaping embedding spaces. Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English. By analyzing the particular impact of style on embedding dispersion, we aim to better understand how language models process stylistic information, contributing to their overall interpretability.

📄 PDF Abstract BibTeX arXiv:2501.00828

Code (1)

evangeliazve/topic_style_embeddings_dispersion 공식 구현

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings

2026-05-11 · Benjamin Icard, Lila Sainero, Alice Breton, Evangelia Zve 외 arxiv

Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embeddings from any language model and retained after LLM rewriting. We inve…

Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

2022-03-03 · ICLR 2022 4 · Dongsheng Wang, Dandan Guo, He Zhao, Huangjie Zheng 외

A topic model is often formulated as a generative model that explains how each word of a document is generated given a set of topics and document-specific topic proportions. It is focused on capturing the word co-occurre…

parameter estimationWord Embeddings

An Image is Worth $K$ Topics: A Visual Structural Topic Model with Pretrained Image Embeddings

2025-04-14 · Matías Piqueras, Alexandra Segerberg, Matteo Magnani, Måns Magnusson 외

Political scientists are increasingly interested in analyzing visual content at scale. However, the existing computational toolbox is still in need of methods and models attuned to the specific challenges and goals of so…

Comparing Writing Styles using Word Embedding and Dynamic Time Warping

2015-11-05 · Abhinav Tushar, Abhinav Dahiya

The development of plot or story in novels is reflected in the content and the words used. The flow of sentiments, which is one aspect of writing style, can be quantified by analyzing the flow of words. This study explor…

Dynamic Time Warping

Beats of Bias: Analyzing Lyrics with Topic Modeling and Gender Bias Measurements

2024-09-24 · Danqing Chen, Adithi Satish, Rasul Khanbayov, Carolin M. Schuster 외

This paper uses topic modeling and bias measurement techniques to analyze and determine gender bias in English song lyrics. We utilize BERTopic to cluster 537,553 English songs into distinct topics and chart their develo…

Word Embeddings