# Generation, Evaluation, and Explanation of Novelists' Styles with Single-Token Prompts

arXiv: https://arxiv.org/abs/2511.20459 · HTML: https://mlsanity.com/paper/2511.20459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Towards Explainable NLP: A Generative Explanation Framework for Text Classification](https://mlsanity.com/paper/1811.00196/) (2018)
- [Content preserving text generation with attribute controls](https://mlsanity.com/paper/1811.01135/) (2018)
- [Explainable AI: current status and future directions](https://mlsanity.com/paper/2107.07045/) (2021)
- [Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer](https://mlsanity.com/paper/2005.12086/) (2020)
- [Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection](https://mlsanity.com/paper/2103.12450/) (2021)
- [Structured Content Preservation for Unsupervised Text Style Transfer](https://mlsanity.com/paper/1810.06526/) (2018)
- [ComLittee: Literature Discovery with Personal Elected Author Committees](https://mlsanity.com/paper/2302.06780/) (2023)
- [Fine-grained Text Style Transfer with Diffusion-Based Language Models](https://mlsanity.com/paper/2305.19512/) (2023)
- [SMAuC -- The Scientific Multi-Authorship Corpus](https://mlsanity.com/paper/2211.02477/) (2022)
- [Improving Explainable Recommendations with Synthetic Reviews](https://mlsanity.com/paper/1807.06978/) (2018)

## Abstract (arXiv)

Recent advances in large language models have created new opportunities for stylometry, the study of writing styles and authorship. Two challenges, however, remain central: training generative models when no paired data exist, and evaluating stylistic text without relying only on human judgment. In this work, we present a framework for both generating and evaluating sentences in the style of 19th-century novelists. Large language models are fine-tuned with minimal, single-token prompts to produce text in the voices of authors such as Dickens, Austen, Twain, Alcott, and Melville. To assess these generative models, we employ a transformer-based detector trained on authentic sentences, using it both as a classifier and as a tool for stylistic explanation. We complement this with syntactic comparisons and explainable AI methods, including attention-based and gradient-based analyses, to identify the linguistic cues that drive stylistic imitation. Our findings show that the generated text reflects the authors' distinctive patterns and that AI-based evaluation offers a reliable alternative to human assessment. All artifacts of this work are published online.