# Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization

arXiv: https://arxiv.org/abs/2604.26460 · HTML: https://mlsanity.com/paper/2604.26460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [PersonalLLM: Tailoring LLMs to Individual Preferences](https://mlsanity.com/paper/2409.20296/) (2024)
- [PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants](https://mlsanity.com/paper/2506.09902/) (2025)
- [Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors](https://mlsanity.com/paper/2509.14543/) (2025)
- [High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making](https://mlsanity.com/paper/2604.04300/) (2026)

## Abstract (arXiv)

Stylistic personalization - making LLMs write in a specific individual's style, rather than merely adapting to task preferences - lacks evaluation grounded in authorship science. We show that grounding evaluation in authorship verification theory transforms what benchmarks can measure. Drawing on three measurement traditions - LUAR (a trained authorship verification model), an LLM-as-judge with decoupled trait matching, and classical function-word stylometrics - we evaluate four inference-time personalization methods across 50 authors and 1,000 generations. The theory-grounded metric (LUAR) provides what ad hoc alternatives cannot: calibrated baselines (human ceiling 0.756, cross-author floor 0.626) that give scores absolute meaning. All methods score below this floor (0.484-0.508), exposing an authorship gap invisible to uncalibrated metrics. The three metrics produce near-zero pairwise correlations (|r| < 0.07), confirming that without theoretical grounding, metric choice determines conclusions - an LLM judge declares a clear winner while LUAR finds no meaningful differentiation. These findings demonstrate the theory-benchmark cycle in action: authorship theory exposes evaluation failures that ad hoc benchmarks miss.