# Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

arXiv: https://arxiv.org/abs/2501.11549 · HTML: https://mlsanity.com/paper/2501.11549/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 59 of its 91 references that are in the map.
- First posted on arXiv 20 Jan 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 59)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards](https://mlsanity.com/paper/2402.18571/) (2024)
- [MaxMin-RLHF: Alignment with Diverse Human Preferences](https://mlsanity.com/paper/2402.08925/) (2024)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [Eliciting Human Preferences with Language Models](https://mlsanity.com/paper/2310.11589/) (2023)

## Built on by (most cited first, 19 of 19)

- [A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models](https://mlsanity.com/paper/2504.07070/) (2025)
- [Direct Alignment with Heterogeneous Preferences](https://mlsanity.com/paper/2502.16320/) (2025)
- [Pluralistic Off-policy Evaluation and Alignment](https://mlsanity.com/paper/2509.19333/) (2025)
- [Improving Language Model Personas via Rationalization with Psychological Scaffolds](https://mlsanity.com/paper/2504.17993/) (2025)
- [Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity](https://mlsanity.com/paper/2505.11861/) (2025)
- [Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues](https://mlsanity.com/paper/2512.15302/) (2025)
- [Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations](https://mlsanity.com/paper/2503.08035/) (2025)
- [Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users](https://mlsanity.com/paper/2603.16120/) (2026)
- [Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling](https://mlsanity.com/paper/2606.04284/) (2026)
- [Scaling Participation in Modular AI Systems](https://mlsanity.com/paper/2606.07812/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries](https://mlsanity.com/paper/2505.21859/) (2025)
- [PREFINE: Personalized Story Generation via Simulated User Critics and User-Specific Rubric Generation](https://mlsanity.com/paper/2510.21721/) (2025)
- [EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling](https://mlsanity.com/paper/2603.28197/) (2026)
- [Coherence Maximization Improves Pluralistic Alignment](https://mlsanity.com/paper/2606.03110/) (2026)
- [Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast](https://mlsanity.com/paper/2608.06400/) (2026)
- [Inferring Hidden User Models from the Behavior of Personalized LLM Agents](https://mlsanity.com/paper/2609.03815/) (2026)
- [Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation](https://mlsanity.com/paper/2610.04676/) (2026)
- [Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback](https://mlsanity.com/paper/2610.19380/) (2026)

## Abstract (arXiv)

LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey why users prefer responses that are chosen or rejected, so LLMs trained on these datasets cannot tailor responses to varied user needs. To surface these parameters of personalization, we apply abductive reasoning to preference data, inferring needs and interests of users, i.e., personas, that may prefer either response. We test this idea in two steps: Persona Inference (PI), abductively inferring personas of users who prefer chosen or rejected outputs, and Persona Tailoring (PT), training models to tailor outputs to personas from PI. We show: 1) LLMs infer personas accurately explaining why different users may prefer both chosen or rejected outputs; 2) Training on preference data augmented with PI personas via PT boosts personalization and generalizes to supporting user-written personas; and 3) Rejected response personas form harder personalization evaluations, showing PT better aids users with uncommon preferences versus typical alignment methods. We argue for an abductive view of preferences for personalization, asking not only which response is better but when, why, and for whom.