One Token to Sound Like Austen? AI Generates and Explains Literary Style

Kari Jaaskelainen

26 Nov 2025 — 1 min read

Can a single token nudge an AI to channel 19th‑century literary greats? This study says yes—and shows how to judge the results without relying only on human taste.

Researchers fine-tuned large language models so a minimal, single-token prompt could trigger the voice of authors like Dickens, Austen, Twain, Alcott, and Melville, generating fresh sentences in recognizable styles.

To check quality, they trained a transformer-based detector on authentic passages and used it both as a style classifier and as an explanation tool. Combined with syntactic comparisons and explainable AI (attention- and gradient-based views), the system highlights the linguistic cues that drive imitation.

Results: the generated text captures distinctive patterns, and automated evaluation offers a reliable complement to human judgment. All code, models, and examples are publicly available. Paper: https://arxiv.org/abs/2511.20459v1

Paper: https://arxiv.org/abs/2511.20459v1

Register: https://www.AiFeta.com

#AI #NLP #LLM #Stylometry #ExplainableAI #DigitalHumanities #ComputationalLinguistics #Authors

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A