# GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences

arXiv: https://arxiv.org/abs/2510.11952 · HTML: https://mlsanity.com/paper/2510.11952/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 30 of 30)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Aligning to Thousands of Preferences via System Message Generalization](https://mlsanity.com/paper/2405.17977/) (2024)
- [Panacea: Pareto Alignment via Preference Adaptation for LLMs](https://mlsanity.com/paper/2402.02030/) (2024)
- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [Personalized Text Generation with Contrastive Activation Steering](https://mlsanity.com/paper/2503.05213/) (2025)
- [FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users](https://mlsanity.com/paper/2502.19312/) (2025)
- [Review-LLM: Harnessing Large Language Models for Personalized Review Generation](https://mlsanity.com/paper/2407.07487/) (2024)
- [ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning](https://mlsanity.com/paper/2410.23180/) (2024)
- [Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment](https://mlsanity.com/paper/2506.05670/) (2025)
- [MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models](https://mlsanity.com/paper/2409.13935/) (2024)
- [Continuous Output Personality Detection Models via Mixed Strategy Training](https://mlsanity.com/paper/2406.16223/) (2024)
- [Audience-Centric Natural Language Generation via Style Infusion](https://mlsanity.com/paper/2301.10283/) (2023)
- [Personalized Abstractive Summarization by Tri-agent Generation Pipeline](https://mlsanity.com/paper/2305.02483/) (2023)
- [ULMRec: User-centric Large Language Model for Sequential Recommendation](https://mlsanity.com/paper/2412.05543/) (2024)
- [Tuning-Free LLM Can Build A Strong Recommender Under Sparse Connectivity And Knowledge Gap Via Extracting Intent](https://mlsanity.com/paper/2505.10900/) (2025)

## Built on by (most cited first, 3 of 3)

- [Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models](https://mlsanity.com/paper/2606.07877/) (2026)
- [MindTailor: Personalized Emotional Support via Post History-Grounded Case Formulation and Collaborative Refinement](https://mlsanity.com/paper/2606.21930/) (2026)
- [PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs](https://mlsanity.com/paper/2608.01458/) (2026)

## Abstract (arXiv)

Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annotations, we introduce GRAVITY (Generative Response with Aligned Values, Interests, and Traits of You), a framework for generating synthetic, profile-grounded preference data that captures users' interests, values, beliefs, and personality traits. By integrating demographic, cultural, and psychological frameworks -- including Hofstede's cultural dimensions, Schwartz's basic values, the World Values Survey, and Big Five OCEAN traits -- GRAVITY synthesizes preference pairs to guide personalized content generation. We evaluate GRAVITY on book descriptions for 400 Amazon users, comparing it to prompt-based conditioning, standard fine-tuning, and naive synthetic pair generation. Profile-grounded synthetic data consistently improves generation, especially across multiple cultures (USA, Brazil, Japan, India), achieving over 4% higher preference gains across baselines, with user studies showing that GRAVITY outputs are preferred over 86% of the time. Our results show that scenario-grounded synthetic data can capture richer user variation, reduce reliance on costly annotation, and produce more engaging, user-centered content, offering a scalable path for LLM personalization.