mlsanityData to 7 Oct 2026

StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples

arXiv 2410.12757 ↗First posted 16 Oct 2024cs.CL cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both style and content, leading to potential content leakage in the representations. We introduce StyleDistance, a novel approach to training stronger content-independent style embeddings. We use a large language model to create a synthetic dataset of near-exact paraphrases with controlled style variations, and produce positive and negative examples across 40 distinct style features for precise contrastive learning. We assess the quality of our synthetic data and embeddings through human and automatic evaluations. StyleDistance enhances the content-independence of style embeddings, which generalize to real-world benchmarks and outperform leading style representations in downstream applications. Our model can be found at https://huggingface.co/StyleDistance/styledistance .

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 27 of its 56 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

27 of 56 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  9. 2018Neural Network Acceptability Judgmentscited by 952
  10. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  11. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  12. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
15 more
  1. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  2. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  3. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 83
  4. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  5. 2024DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflowscited by 43
  6. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 39
  7. 2023Learning Interpretable Style Embeddings via Prompting LLMscited by 29
  8. 2021A Deep Metric Learning Approach to Account Linkingcited by 24
  9. 2023ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfercited by 18
  10. 2024StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elementscited by 18
  11. 2021Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Frameworkcited by 17
  12. 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysiscited by 14
  13. 2024Authorship Style Transfer with Policy Optimizationcited by 11
  14. 2023Learning to Generate Text in Arbitrary Writing Stylescited by 9
  15. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 14.

32 papers.

Sort:

By area:

  1. 2025Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domainscited by 7
  2. 2025Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Modelscited by 6
  3. 2025NSF-SciFy: Mining the NSF Awards Database for Scientific Claimscited by 2
  4. 2025The Impact of Automatic Speech Transcription on Speaker Attributioncited by 2
  5. 2025Multiple Choice Learning of Low-Rank Adapters for Language Modelingcited by 2
  6. 2025Evaluating Style-Personalized Text Generation: Challenges and Directionscited by 2
  7. 2025A stylometric analysis of speaker attribution from speech transcriptscited by 2
  8. 2026Benchmarking Machine Translation on Chinese Social Media Textscited by 2
  9. 2025mStyleDistance: Multilingual Style Embeddings and their Evaluationcited by 1
  10. 2025Team "better_call_claude": Style Change Detection using a Sequential Sentence Pair Classifiercited by 1
  11. 2025One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verificationcited by 1
  12. 2026CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluationcited by 1
20 more
  1. 2026AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixingcited by 1
  2. 2026IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variationcited by 1
  3. 2026Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategiescited by 1
  4. 2026Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Stylecited by 1
  5. 2026Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fictioncited by 1
  6. 2025Challenging Assumptions in Learning Generic Text Style Embeddingscited by 0
  7. 2025Attacks on Machine-Text Detectors Retain Stylistic Fingerprintscited by 0
  8. 2025Quantifying Misattribution Unfairness in Authorship Attributioncited by 0
  9. 2025Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Expertscited by 0
  10. 2025RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewritingcited by 0
  11. 2025Navigating the Synchrony-Stability Frontier in Adaptive Chatbotscited by 0
  12. 2025iBERT: Interpretable Embeddings via Sense Decompositioncited by 0
  13. 2025Capturing Classic Authorial Style in Long-Form Story Generation with GRPO Fine-Tuningcited by 0
  14. 2026Interpreting Style Representations via Style-Eliciting Promptscited by 0
  15. 2026Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversioncited by 0
  16. 2026STEB: Style Text Embedding Benchmarkcited by 0
  17. 2026Writing Style Similarity Reflects Academic Genealogycited by 0
  18. 2026Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experiencecited by 0
  19. 2026Can Activation Steering Capture Multidimensional Authorship Style?cited by 0
  20. 2026FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generationcited by 0