arXiv Computation and Language

Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approaches

The paper examines how different author representations affect zero‑shot authorship attribution (AA). It compares a label‑only prompting baseline with three strategies: representative writing samples, LLM‑generated descriptions, and style embeddings (LISA). The study finds that incorporating author‑specific representations improves performance, with a two‑stage LISA framework achieving the best results, while LLM‑generated descriptions offer a more compact but slightly less accurate alternative.

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

llms rag benchmarks

arXiv AI

Jun 10

Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion

arXiv:2606. 10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence operations, motivating the need for robust detectors.

By Rafael Rivera Soto, Barry Chen, Nicholas Andrews

llms benchmarks safety

arXiv AI

Sep 2

One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification

arXiv:2510.13302v4 Announce Type: replace-cross Abstract: Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, i...

By Pablo Miralles-Gonz\'alez, Javier Huertas-Tato, Alejandro Mart\'in, David Camacho

llms

arXiv AI

Sep 7

Can Activation Steering Capture Multidimensional Authorship Style?

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.

By Hieu Tran, Calvin Bao, Marine Carpuat

llms benchmarks

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

llms reinforcement-learning fine-tuning

arXiv AI

Jun 10

READER: Robust Evidence-based Authorship Decoding via Extracted Representations

arXiv:2606. 10794v1 Announce Type: new Abstract: As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model generated a given black-box response?

By Jiaxu Liu, Sunnan Mu, Dong Huang, Liuyin Wang, Jing Shao, Jie Zhang

llms agents benchmarks

arXiv AI

Jun 2

AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection

arXiv:2606. 00016v1 Announce Type: cross Abstract: Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals.

By Aria Nourbakhsh, Adelaide Danilov, Christoph Schommer, Salima Lamsiyah

llms benchmarks

Hugging Face Trending Papers

Aug 18

When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era

Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this assumption is challenged by dis...

llms rag fine-tuning benchmarks

arXiv Computer Vision

Sep 30

Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning

arXiv:2609.37656v1 Announce Type: new Abstract: Large vision-language models (LVLMs) exhibit strong reasoning capabilities, yet the visual and textual evidence supporting the generated responses rema...

By Bowen Yuan, Danny Wang, Ruihong Qiu, Zijian Wang, Zi Huang

llms multimodal benchmarks

arXiv AI

Aug 25

LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space

arXiv:2608.23124v1 Announce Type: cross Abstract: Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support too...

By Jinghui Zhang, Lang Gao, Ao Li, Mingzhe Li, Ruihong Zeng, Zirui Song, Kentaro Inui, Xiuying Chen

fine-tuning

arXiv Machine Learning

Oct 3

TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models

TrueMuse is a new benchmark designed to evaluate data attribution in text-to-music models. It consists of a controlled dataset created by fine‑tuning three diffusion‑based models on curated attribution samples, providing known attribution targets. The benchmark covers four settings—melodic structure, timbral characteristics, artist‑level style, and genre‑level patterns—across 133 attributes, 648 models, and 95,456 generated samples, and is used to assess existing black‑box attribution methods along several dimensions.

By Jiawei Yu, Jian Liu

diffusion fine-tuning benchmarks

arXiv AI

Jun 12

Authorship Attribution in Multilingual Machine-Generated Texts

arXiv:2508. 01656v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult.

By Lucio La Cava, Dominik Macko, R\'obert M\'oro, Ivan Srba, Andrea Tagarelli

llms

Related stories