arXiv AI By Hieu Tran, Calvin Bao, Marine Carpuat

Can Activation Steering Capture Multidimensional Authorship Style?

Read the original on arXiv AI →

The paper investigates whether activation steering can capture the complex, multidimensional nature of authorship style. By using structured contrastive prompting along rhetorically motivated dimensions, the authors construct rich style representations directly in activation space, revealing a shared authorship backbone with aspect‑specific residuals. They propose Aspect‑Aware Activation Steering (A3S), a training‑free framework that merges per‑aspect contrastive directions, employs interference‑aware aggregation, and tunes steering strength per instance, achieving better authorship style transfer and outperforming a trained baseline on out‑of‑domain benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Sep 18

Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations

The paper introduces a training‑free method for uncovering prompt‑conditional stylistic axes in large language models (LLMs). By repeatedly sampling completions of a single prompt at high temperature and applying Principal Component Analysis (PCA) to the pooled hidden activations, the authors automatically label the resulting axes using the extreme (pole) generations. Validation against 245 human‑elicited stylistic annotations shows that, for the Qwen‑3.5‑4B‑Instruct model, the top two axes align with human dimensions with 72.8% precision and 43.6% macro‑recall, and 75.6% of validity ratings confirm the axes’ polar generations, while other models exhibit varying degrees of discoverability.

By Ajit Mallavarapu, Ziwei Gu
arXiv AI
Sep 17

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

AuthorMix is a lightweight, modular framework for authorship style transfer that uses layer‑wise adapter mixing. It trains individual style‑specific LoRA adapters on a small set of high‑resource authors, enabling rapid adaptation to new target styles with only a few examples. The method achieves the highest combined style‑meaning score among baselines, including GPT‑5.1, and improves meaning preservation, as confirmed by human evaluation.

By Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan, Alexander Koller
arXiv Computation and Language
Sep 2

Evaluating Style-Personalized Text Generation: Challenges and Directions

The paper "Evaluating Style-Personalized Text Generation: Challenges and Directions" examines the difficulties of assessing text that is tailored to individual users’ styles. It critiques common metrics such as BLEU, embeddings, and LLM-as-judges, and introduces a style discrimination benchmark covering domain discrimination, authorship attribution, and LLM-generated personalized versus non-personalized discrimination across eight writing tasks. The study finds that ensembles of diverse evaluation metrics outperform single-evaluator approaches and offers guidance for reliable assessment of style-personalized generation.

By Anubhav Jangra, Bahareh Sarrafzadeh, Silviu Cucerzan, Adrian de Wynter, Sujay Kumar Jauhar