# PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluation

arXiv: https://arxiv.org/abs/2506.04551 · HTML: https://mlsanity.com/paper/2506.04551/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2025.

## Built on by (most cited first, 12 of 12)

- [Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback](https://mlsanity.com/paper/2602.12612/) (2026)
- [Verifiable User Simulation for Search and Recommendation Systems](https://mlsanity.com/paper/2606.14474/) (2026)
- [How Well Do Large Language Models Capture Human Personality?](https://mlsanity.com/paper/2606.18263/) (2026)
- [PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback](https://mlsanity.com/paper/2601.03149/) (2026)
- [Enriching Semantic Profiles into Knowledge Graph for Recommender Systems Using Large Language Models](https://mlsanity.com/paper/2601.08148/) (2026)
- [Bridging Semantic Understanding and Popularity Bias with LLMs](https://mlsanity.com/paper/2601.09478/) (2026)
- [MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation](https://mlsanity.com/paper/2603.25126/) (2026)
- [Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems](https://mlsanity.com/paper/2605.05250/) (2026)
- [Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility](https://mlsanity.com/paper/2605.06856/) (2026)
- [A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators](https://mlsanity.com/paper/2609.25572/) (2026)
- [PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems](https://mlsanity.com/paper/2610.13989/) (2026)
- [SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems](https://mlsanity.com/paper/2610.18308/) (2026)

## Abstract (arXiv)

Traditional offline evaluation methods for recommender systems struggle to capture the complexity of modern platforms due to sparse behavioural signals, noisy data, and limited modelling of user personality traits. While simulation frameworks can generate synthetic data to address these gaps, existing methods fail to replicate behavioural diversity, limiting their effectiveness. To overcome these challenges, we propose the Personality-driven User Behaviour Simulator (PUB), an LLM-based simulation framework that integrates the Big Five personality traits to model personalised user behaviour. PUB dynamically infers user personality from behavioural logs (e.g., ratings, reviews) and item metadata, then generates synthetic interactions that preserve statistical fidelity to real-world data. Experiments on the Amazon review datasets show that logs generated by PUB closely align with real user behaviour and reveal meaningful associations between personality traits and recommendation outcomes. These results highlight the potential of the personality-driven simulator to advance recommender system evaluation, offering scalable, controllable, high-fidelity alternatives to resource-intensive real-world experiments.