mlsanityData to 14 Oct 2026

Learning Interpretable Style Embeddings via Prompting LLMs

arXiv 2305.12696 ↗First posted 22 May 2023cs.CLcited by 30

Not on the map. Why?

Abstract (arXiv)

Style representation learning builds content-independent representations of author style in text. Stylometry, the analysis of style in text, is often performed by expert forensic linguists and no large dataset of stylometric annotations exists for training. Current style representation learning uses neural methods to disentangle style from content to create style vectors, however, these approaches 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 create a synthetic dataset and train human-interpretable style representations we call LISA embeddings. We release our synthetic stylometry dataset and our interpretable style models as resources.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 45 of its 74 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

45 of 74 references.

References · 45

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2020Scaling Laws for Neural Language Modelscited by 6,586
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  10. 2020Supervised Contrastive Learningcited by 2,829
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  12. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
33 more
  1. 2020Concept Bottleneck Modelscited by 1,032
  2. 2018Neural Network Acceptability Judgmentscited by 958
  3. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  4. 2022Large Language Models Can Self-Improvecited by 664
  5. 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 564
  6. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
  7. 2013Do Deep Nets Really Need to be Deep?cited by 474
  8. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
  9. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 312
  10. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  11. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
  12. 2018Hate Speech Dataset from a White Supremacy Forumcited by 198
  13. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  14. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  15. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  16. 2018Style Transfer Through Back-Translationcited by 124
  17. 2019Automatically Neutralizing Subjective Bias in Textcited by 105
  18. 2020ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformationscited by 101
  19. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 86
  20. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  21. 2020Investigating African-American Vernacular English in Transformer-Based Text Generationcited by 53
  22. 2016Personalized Machine Translation: Preserving Original Author Traitscited by 47
  23. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 40
  24. 2019Domain Adaptive Text Style Transfercited by 25
  25. 2021A Deep Metric Learning Approach to Account Linkingcited by 24
  26. 2021Unsupervised Neural Machine Translation with Generative Language Models Onlycited by 24
  27. 2022APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversationscited by 23
  28. 2019Learning Invariant Representations of Social Media Userscited by 21
  29. 2020The Importance of Suppressing Domain Style in Authorship Analysiscited by 18
  30. 2021Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Stylescited by 18
  31. 2021Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Frameworkcited by 17
  32. 2019Similarity Learning for Authorship Verification in Social Mediacited by 11
  33. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 11; 2026: 8.

30 papers.

Sort:

By area:

  1. 2024Can Large Language Models Identify Authorship?cited by 41
  2. 2024StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examplescited by 35
  3. 2024CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Followingcited by 33
  4. 2024Bayesian Concept Bottleneck Models with LLM Priorscited by 17
  5. 2026Human-AI Co-design for Clinical Prediction Modelscited by 9
  6. 2024Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attributioncited by 7
  7. 2025HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generationcited by 7
  8. 2025Fundamental Limits of Perfect Concept Erasurecited by 6
  9. 2023ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfercited by 5
  10. 2024Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Interventioncited by 5
  11. 2025PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encodercited by 5
  12. 2024Speaker Verification in Agent-Generated Conversationscited by 4
18 more
  1. 2025Residualized Similarity for Faithfully Explainable Authorship Verificationcited by 4
  2. 2024CAVE: Controllable Authorship Verification Explanationscited by 3
  3. 2026Personalized Benchmarking: Evaluating LLMs by Individual Preferencescited by 3
  4. 2024WordDecipher: Enhancing Digital Workspace Communication with Explainable AI for Non-native English Speakerscited by 2
  5. 2025The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributescited by 2
  6. 2026IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variationcited by 2
  7. 2023Authorship identification under domain shift: a survey of stylistic measures and learned author representationscited by 1
  8. 2025mStyleDistance: Multilingual Style Embeddings and their Evaluationcited by 1
  9. 2025LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representationscited by 1
  10. 2025What's in a prompt? Language models encode literary style in prompt embeddingscited by 1
  11. 2025Better Call Claude: Can LLMs Detect Changes of Writing Style?cited by 1
  12. 2025Stylometry recognizes human and LLM-generated texts in short samplescited by 0
  13. 2025XAM: Interactive Explainability for Authorship Attribution Modelscited by 0
  14. 2026Differentially-Private Text Rewriting reshapes Linguistic Stylecited by 0
  15. 2026Interpreting Style Representations via Style-Eliciting Promptscited by 0
  16. 2026STEB: Style Text Embedding Benchmarkcited by 0
  17. 2026Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generationcited by 0
  18. 2026Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approachescited by 0