Stylistic Fidelity

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 43

All topics

Reason in Style: Discovering and Controlling Style in Language Models
Sep 30, 2026Ioana Marinescu, Eric Karl Oermann, Kyunghyun ChoStylistic Fidelity Style
NYU · NYU & NYU Langone Health
Where the Evidence Lives: Auditing AI Companions' Self-Descriptions
Sep 30, 2026Seiya Ikeda, Shin-nosuke IshikawaModel Auditing Stylistic Fidelity
AI Consulting Division, Mamezo Co., Ltd. Tokyo, Japan · AI Technical Sector, Mamezo Co., Ltd. Tokyo, Japan · Graduate School of Artificial Intelligence and Science, Rikkyo University Tokyo, Japan
Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat?
Sep 23, 2026AbdulRahman A. Morsy, Aya ZiriklyPoetry Arabic Natural Language Processing
Department of Computer Science, School of Engineering and Applied Sciences, George Washington University, Washington DC, United States · Department of Computer Science, School of Engineering and Applied Sciences, George Washington University, Washington, DC, United States · Center for Speech and Language Processing, Whiting School of Engineering, Johns Hopkins University, Baltimore MD, United States +1
I Am No One: Style-Aware Paraphrasing for Text Anonymization
Sep 14, 2026Ahmed Sohair Khan, Estrid He, Monica Wachowicz +1Anonymization Stylometric
RMIT University, Melbourne, Australia
Syntactic Patterns and Stylistic Functions in Narrative Prose: A Rule-Based and Machine-Learning Approach
Sep 7, 2026Stefana JanicijevicSyntactic Structure Stylometric
Value Over Language Model: Detecting Original Contribution in Writing
Sep 1, 2026Vibhhu Sharma, Thorsten Joachims, Sarah DeanHuman-Written Text Large Language Model Generation
Cornell University
Patterning in Practice: Debiasing Reward Models with Susceptibilities
Sep 1, 2026George Wang, Elizabeth Donoway, Daniel MurfetProgress Reward Modeling Preference Alignment Learning
Resolution
Conducting Stylistic Analysis of Paintings through an Art-History Agent
Aug 30, 2026Marc S. Walton, Astrid HarthArtistic Ownership Art
Museum Studies Programme, The University of Hong Kong, Hong Kong SAR · Department of Chinese and History, City University Hong Kong, Hong Kong SAR
Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation
Aug 3, 2026Fengxian Ji, Yuke Li, Jingpu Yang +8Scientific Ideation Llm-As-A-Judge
Wuhan University · Northeastern · Zhongguancun Academy +3
Occluded Oculus: Operationalizing Stylistic Obscurement
Jul 27, 2026Robert DilworthObfuscation Attack Stealthiness
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA
PrefReward: Learning User Preference Matrix for Personalized Text Generation
Jul 23, 2026Yue Wu, Chengbing Wang, Yimeng Bai +3Large Language Model Personalization Text Generation
University of Science and Technology of China · The Chinese University of Hong Kong · National University of Singapore
Back to Back with a Copy: A Computational Analysis of AI-Generated Visual Contemporary Art Pastiches
Jul 22, 2026Anca Dinu, Andreiana Mihail, Andra-Maria Florescu +2Stylistic Fidelity Art
University of Bucharest, Bucharest, Romania
Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law
Jun 30, 2026Noah Scharrenberg, Chang SunStylistic Fidelity Copyright Defenses
Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands. · Contractuo, Eindhoven, The Netherlands.
Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
Jun 25, 2026Zhihao Wen, Yixin Yang, Bojian Wu +4Stylization Cross-View
Guangdong Provincial Key Laboratory of Visual Media and Multidimensional Intelligence, CSSE, Shenzhen University, China · Tencent Games, China · The Hebrew University of Jerusalem, Israel +1
Leveraging Large Language Models to Obscure Code Stylometry: A Comparative Study of GPT-3.5 and GPT-4
Jun 21, 2026Saman Pordanesh, Benjamin TanStylometric Authorship
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
Jun 18, 2026Shaghayegh Kolli, Timo Cavelius, Nafiseh Nikeghbal +2Large Language Model Bias Stylistic Fidelity
Technical University of Munich · Munich Center for Machine Learning · Princeton Center for Information and Technology Policy
Interpreting Style Representations via Style-Eliciting Prompts
Jun 4, 2026Junghwan Kim, David JurgensStylistic Fidelity Style
University of Michigan
Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation
May 30, 2026Ruiqi Zhang, Lingxiang Wang, Hainan Zhang Zhiming ZhengReasoning Benchmark Stylistic Fidelity
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University · School of Artificial Intelligence, Beihang University
Measuring, Localizing, and Ablating Alignment Signatures in LLMs
May 28, 2026Aniket Anand, Janvijay Singh, Zhewei Sun +2Large Language Model Alignment Machine-Generated Text Detection
University of Chicago · University of Illinois at Urbana-Champaign · Toyota Technological Institute at Chicago
Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
May 28, 2026Hyojeong Yu, Hyukhun Koh, Minsung Kim +1Stylistic Fidelity Motion-Language Alignment
Seoul National University Seoul, Korea
Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction
May 27, 2026Zehan Li, Yutong Zhu, Siyang Wu +2Narrative Generation Narratives
Knowledge Lab, University of Chicago
Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics
May 26, 2026Jiashuo Wang, Fenggang Yu, Jian Wang +6Stylistic Fidelity Cultural Awareness
Department of Computing, Hong Kong Polytechnic University · Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Department of Language Science and Technology, Hong Kong Polytechnic University +3
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
May 24, 2026Xianglin Yang, Bryan Hooi, Gelei Deng +2Llm-As-A-Judge Attacker Large Language Model
School of Computing, National University of Singapore, Singapore · Nanyang Technological University, Singapore
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
May 22, 2026Xiao Cao, Yansong Qu, Xiangzhen +7Inpainting Photorealistic Style Transfer
The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation
May 17, 2026Ninad Joshi, Ashutosh Ranjan, Vivek Srivastava +1Text-To-Image Diffusion Models Stylistic Fidelity
TCS Research, India
Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
May 15, 2026Hongxi Li, Tong Wang, Chengjing Wu +6Diffusion-Based Image Editing Text-To-Image Diffusion Models
1MT Lab, Meitu Inc., Beijing, China · School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China
Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
May 11, 2026Benjamin Icard, Lila Sainero, Alice Breton +2Stylistic Fidelity Authorship
LIP6, Sorbonne University, CNRS, France · Infopro Digital, France
A Decomposed Retrieval-Edit-Rerank Framework for Chord Generation
May 8, 2026Qiqi He, Dichucheng Li, Xiaoheng Sun +1Sheet Music Stylistic Fidelity
NetEase Cloud Music Shanghai, China · Individual Researcher Hong Kong, China
Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation
May 7, 2026Siyuan Li, Aodu Wulianghai, Xi Lin +6Content Moderation Human-Written Text
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China
MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs
May 5, 2026Tung Sum Thomas Kwok, Qian Qian, Xiaofeng Lin +8Stylistic Fidelity
University of California, Los Angeles CA 90095, USA · Optum AI, USA
Stylistic Attribute Control in Latent Diffusion Models
May 4, 2026Max Reimann, Benito Buchheim, Jürgen DöllnerDiffusion-Based Image Editing Text-To-Image Diffusion Models
Hasso-Plattner-Institute, University of Potsdam, Germany
Differentially-Private Text Rewriting reshapes Linguistic Style
Apr 29, 2026Stefan ArnoldStylistic Fidelity Privacy
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization
Apr 29, 2026Yash Ganpat SawantAuthorship Stylistic Fidelity
Independent AI Researcher
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
Apr 27, 2026Connor Baumler, Calvin Bao, Huy Nghiem +3Stylistic Fidelity Ai-Assisted Writing
University of Maryland
An audio-to-analysis pipeline with certified transcription for information-theoretic profiling of the piano repertoire
Apr 25, 2026Fred Jalbert-DesforgesInstrument Stylometric
Independent Music Analysis Researcher Creator of CYGNUS & LYRA Montreal, Quebec
Towards a Linguistic Evaluation of Narratives: A Quantitative Stylistic Framework
Apr 21, 2026Alessandro MaistoNarratives Evaluation Metrics
Università degli Studi di Salerno, Via Giovanni Paolo II, 132, 84084 Fisciano (SA), Italia
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
Apr 20, 2026Marcello Galisai, Susanna Cifani, Francesco Giarrusso +5Large Language Model Safety Adversarial Evaluation
DEXAI – Icaro Lab · Sapienza University of Rome · Sant’Anna School of Advanced Studies
Coexisting Tempo Traditions in Beethoven's Piano and Cello Sonatas: A K-means Clustering Analysis of Recorded Performances, 1930-2012
Apr 17, 2026Ignasi SoleBeethoven K-Means
Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset
Apr 17, 2026Yuhai Deng, Huimin She, Wei Shen +4Photorealistic Style Transfer Style
VCIP, School of Computer Science, Nankai University · OPPO AI Center, OPPO Inc. · Nankai International Advanced Research Institute (Shenzhen Futian)
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance
Apr 17, 2026Hamed Ouattara, Pierre Duthon, Pascal Houssam Salmane +2Self-Supervised Learning Appearance
Intelligent Transportation Systems Research Team, Cerema, 8 rue Bernard Palissy, 63017 Clermont-Ferrand, France · Intelligent Transportation Systems Research Team, Cerema, 1 avenue du Colonel Roche, 31400 Toulouse, France · Clermont Auvergne INP, Universit´e Clermont Auvergne, Institut Pascal, CNRS, 4 Avenue Blaise Pascal, 63178 Clermont-Ferrand, France
Benchmarking Machine Translation on Chinese Social Media Texts
Jan 30, 2026Kaiyan Zhao, Zheyong Xie, Zhongtao Miao +3Multilingual Benchmark Social Media Posts
1The University of Tokyo · 2Xiaohongshu Inc. · 3Tsinghua University
Text-Conditioned Background Generation for Editable Multi-Layer Documents
Dec 19, 2025Taewon Kang, Joseph K J, Chris Tensmeyer +4Precise Editing High-Fidelity Conditional Generation
University of Maryland at College Park, United States · Adobe Research, United States
Evaluating Style-Personalized Text Generation: Challenges and Directions
Aug 8, 2025Anubhav Jangra, Bahareh Sarrafzadeh, Silviu Cucerzan +2Stylistic Fidelity Text Generation
Columbia University, USA · Microsoft, USA · The University of York, UK

Sep 30, 2026, cs.CLJ/K move · Enter open · S save

Reason in Style: Discovering and Controlling Style in Language Models

Ioana Marinescu, Eric Karl Oermann, Kyunghyun Cho

NYU · NYU & NYU Langone Health

Stylistic Fidelity Style Mathematical Reasoning Benchmarks Reasoning Skills Teacher Unsupervised

Open paper AskPDF arXiv

Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content and style from language models' outputs and validate its effectiveness on math questions in a controlled setting. By applying this method to over 100K verified traces from nine distinct teacher models, we discover six recurring yet imbalanced styles. We then fine-tune smaller student models to follow these styles when explicitly conditioned on them, using importance weighting to balance the contribution of the styles represented in the corpus. This approach improves Pass@

k

over standard fine-tuning on the same data across six math reasoning benchmarks, demonstrating that we can diversify the style of answers effectively. We confirm that this also results in strong correspondence between requested and realized styles. We find that style affects correctness: the probability of solving a problem depends on the style we condition on, and different problems benefit from different styles. In summary, our results show that stylistic variation in model-generated data can be discovered in an unsupervised way, and made explicit, providing a source of both control and improved reasoning performance.

Momentum

Related topics

Latest papers 43