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

arXiv: https://arxiv.org/abs/2608.23124 · HTML: https://mlsanity.com/paper/2608.23124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.01161/) (2017)
- [Personalized Text Generation with Contrastive Activation Steering](https://mlsanity.com/paper/2503.05213/) (2025)
- [CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM](https://mlsanity.com/paper/2401.03512/) (2024)
- [DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing](https://mlsanity.com/paper/2501.14371/) (2025)
- [Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness](https://mlsanity.com/paper/2510.04484/) (2025)
- [The Cylindrical Representation Hypothesis for Language Model Steering](https://mlsanity.com/paper/2605.01844/) (2026)
- [From Individuals to Crowds: Dual-Level Public Response Prediction in Social Media](https://mlsanity.com/paper/2508.00497/) (2025)

## Abstract (arXiv)

Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary analysis. However, existing approaches to author modeling and personalization often represent writing behavior as independent labels, requiring large-scale corpus collection or fine-tuning for each author or stylistic category. Such formulations are costly, difficult to interpret, and poorly suited for generalizing across authors. Inspired by the Big Five model's dimensional view of personality, we propose LiteraryBigFive, a framework that reframes authorial writing characteristics as coordinates within a unified and interpretable space. In this space, we derive each interpretable axis (e.g., Classicism, Emotionality) from activation-space contrasts between author-written and neutral passages, yielding distinct stylistic dimensions that allow texts or authors to be positioned within a five-dimensional system. Beyond localizing different authors, we further introduce an interpretable steering mechanism, which adaptively guides text generation toward target coordinates to perform author-personalized writing. Experimental results show that LiteraryBigFive improves authorial expressiveness while preserving semantic fidelity. The derived author per-axis scores strongly correlate with real-world literary consensus, offering transparent and interpretable explanations of author-specific generation behavior: https://github.com/Znull-1220/LiteraryBigFive.