The paper introduces GLASS, a training‑free framework that personalizes text generation by combining global user‑style priors extracted with sparse autoencoders and local contrastive style vectors built from clustered interaction scenarios. During inference, GLASS injects these global and local vectors into different model layers, achieving context‑aware personalization without retrieval or parameter updates. Experiments on LaMP and LongLaMP datasets demonstrate that GLASS surpasses retrieval, fine‑tuning, and other steering baselines on ROUGE metrics and LLM‑as‑judge evaluations, and its SAE‑based representations show robustness to topic and length shifts, indicating better disentanglement of style from content.
By Liuji Chen, Zeyu Zhang, Xinyuan Zhang, Shuai Nie, Qiang Liu, Shu Wu, Liang Wang
The paper introduces PerFine, a training‑free critique‑refine framework that improves large language model personalization. In each iteration, a generator drafts text conditioned on a retrieved user profile, while a critic—also conditioned on the same profile—provides structured feedback on tone, vocabulary, sentence structure, and topicality. The generator revises the draft, and a knockout strategy selects the best version across iterations; additional inference‑time techniques such as Best‑of‑N and Topic Extraction further balance quality and efficiency. Experiments on Yelp, Goodreads, and Amazon datasets show PerFine consistently outperforms existing retrieval‑augmented methods like PGraphRAG, achieving G‑Eval gains of +8.5‑12% and steady improvements over 3‑5 refinement iterations.
By Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao, Gayathri Akkinapalli, Franck Dernoncourt, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed
arXiv:2601. 06362v2 Announce Type: replace Abstract: Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve.
By Yutong Song, Jiang Wu, Shaofan Yuan, Chengze Shen, Jian Wang, Yu Wang, Nikil Dutt, Amir M. Rahmani
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
arXiv:2510.17881v4 Announce Type: replace
Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We int...
By Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li, Pei Chen, Changlong Yu, Qingyu Yin, Priyanka Nigam, Meng Jiang, Bing Yin
arXiv:2610.09795v1 Announce Type: new
Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap...
By Huayi Lai, Jicheng Yang, Min Yi, Chong Meng
The paper investigates how to reduce the per-user adaptation burden in personalized large language models by separating reusable personalization capacity from user-specific adjustments. Through empirical studies, it shows that shared low‑rank factors can capture much of the cross‑user structure, while a tiny user code suffices for individual correction. The proposed LINEUP framework achieves state‑of‑the‑art performance on six personalized tasks while using only eight scalars per user compared to millions of private‑LoRA parameters.
By Songyuan Sui, Srikanth Malla, Chiho Choi, Joon Hee Choi
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:2510.12041v3 Announce Type: replace
Abstract: Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecifie...
By Ruibo Chen, Jiacheng Pan, Heng Huang, Zhenheng Yang
The paper introduces GAP-DPO, a method for personalizing large language models by selecting preference pairs based on gradient alignment with user utility. It formalizes personalized preference learning as a geometry‑aligned optimization problem, showing that off‑policy sampling can shift DPO updates from error correction to reinforcement when preference margins align with utility gradients. Experiments demonstrate that GAP‑DPO improves stylistic fidelity, preference alignment, and overall generation quality over standard DPO variants.
By Ruoming Jin, Xinyu Li, Hao Zhou, Jianfeng Zhu, Ruixin Guo, Feodor Dragan, Lei Xu, Haixun Wang, Yang Zhou
arXiv:2610.19166v1 Announce Type: new
Abstract: Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that co...
By Anubhav Jangra, Adrian de Wynter
PLUME is a lightweight framework for personalizing large language models by learning a shared task-specific subspace from aggregated user data and then training only a small square matrix for each user within that subspace. The approach introduces cross-layer shared parameters and rank‑1 residual terms to reduce redundancy while preserving expressiveness. Experiments on personalized text generation benchmarks show that PLUME matches or outperforms strong baselines while cutting per‑user parameters by over 95%.
By Xinyu Li, Hao Zhou, Jianfeng Zhu, Julina Maharjan, Ruixin Guo, Feodor Dragan, Ruoming Jin