# Interpreting Style Representations via Style-Eliciting Prompts

arXiv: https://arxiv.org/abs/2606.05716 · HTML: https://mlsanity.com/paper/2606.05716/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Can Large Language Models Identify Authorship?](https://mlsanity.com/paper/2403.08213/) (2024)
- [Few-Shot Detection of Machine-Generated Text using Style Representations](https://mlsanity.com/paper/2401.06712/) (2024)
- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [Eliciting Language Model Behaviors with Investigator Agents](https://mlsanity.com/paper/2502.01236/) (2025)
- [Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification](https://mlsanity.com/paper/2310.08123/) (2023)
- [Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles](https://mlsanity.com/paper/2109.03158/) (2021)
- [ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer](https://mlsanity.com/paper/2308.15459/) (2023)
- [StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements](https://mlsanity.com/paper/2408.15666/) (2024)
- [Can Authorship Representation Learning Capture Stylistic Features?](https://mlsanity.com/paper/2308.11490/) (2023)
- [TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://mlsanity.com/paper/2406.15586/) (2024)
- [Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors](https://mlsanity.com/paper/2509.14543/) (2025)
- [Separating Style from Substance: Enhancing Cross-Genre Authorship Attribution through Data Selection and Presentation](https://mlsanity.com/paper/2408.05192/) (2024)
- [Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution](https://mlsanity.com/paper/2409.07072/) (2024)
- [InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification](https://mlsanity.com/paper/2407.12882/) (2024)
- [Evaluating Style-Personalized Text Generation: Challenges and Directions](https://mlsanity.com/paper/2508.06374/) (2025)
- [Style, Content, and the Success of Ideas](https://mlsanity.com/paper/2201.03174/) (2022)

## Abstract (arXiv)

Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explain these representations by generating natural language descriptions with large language models (LLMs) conditioned on input text. However, such descriptions are often prone to the LLM's biases and hallucinations, and they lack an explicit objective and practical utility. In this work, we propose a novel framework for interpreting style representations through style-eliciting prompts: natural language instructions designed to steer LLMs to generate text that reflects specific stylistic attributes. We curate 1,010 distinct style features spanning 26 stylistic categories and construct a dataset by prompting an LLM to generate text conditioned on these features. Using this data, we train a decoder to generate a style prompt from the style representation of the generated text. We evaluate our approach on three tasks: (1) recovering original style prompts from generated text, (2) generating text in the same style using the recovered prompts, and (3) steering LLM outputs to match the style of human-written texts. Experiments demonstrate that our method consistently outperforms strong baselines that directly prompt LLMs with target text, achieving superior performance in both style description and style imitation. These results highlight that style-eliciting prompts can provide a practical and interpretable interface to stylistic information encoded in style representations.