mlsanityData to 14 Oct 2026

Aligning LLM with human travel choices: a persona-based embedding learning approach

arXiv 2505.19003 ↗First posted 25 May 2025cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

The advent of large language models (LLMs) presents new opportunities for travel demand modeling. However, behavioral misalignment between LLMs and humans presents obstacles for the usage of LLMs, and existing alignment methods are frequently inefficient or impractical given the constraints of typical travel demand data. This paper introduces a novel framework for aligning LLMs with human travel choice behavior, tailored to the current travel demand data sources. Our framework uses a persona inference and loading process to condition LLMs with suitable prompts to enhance alignment. The inference step establishes a set of base personas from empirical data, and a learned persona loading function driven by behavioral embeddings guides the loading process. We validate our framework on the Swissmetro mode choice dataset, and the results show that our proposed approach significantly outperformed baseline choice models and LLM-based simulation models in predicting both aggregate mode choice shares and individual choice outcomes. Furthermore, we showcase that our framework can generate insights on population behavior through interpretable parameters. Overall, our research offers a more adaptable, interpretable, and resource-efficient pathway to robust LLM-based travel behavior simulation, paving the way to integrate LLMs into travel demand modeling practice in the future.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 41 of its 69 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

41 of 69 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  7. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  8. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  9. 2023Can Large Language Models Transform Computational Social Science?cited by 250
  10. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 249
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  12. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
29 more
  1. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 180
  2. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  4. 2022Thinking Fast and Slow in Large Language Modelscited by 137
  5. 2023Investigating the Catastrophic Forgetting in Multimodal Large Language Modelscited by 119
  6. 2024Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generationcited by 100
  7. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  8. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 92
  9. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 81
  10. 2025LLM Generated Persona is a Promise with a Catchcited by 81
  11. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 49
  12. 2023Diminished Diversity-of-Thought in a Standard Large Language Modelcited by 45
  13. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  14. 2024Centaur: a foundation model of human cognitioncited by 36
  15. 2024The illusion of artificial inclusioncited by 34
  16. 2020A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretabilitycited by 22
  17. 2024Be More Real: Travel Diary Generation Using LLM Agents and Individual Profilescited by 22
  18. 2024Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Modelscited by 22
  19. 2024Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Frameworkcited by 19
  20. 2020Theory-based residual neural networks: A synergy of discrete choice models and deep neural networkscited by 15
  21. 2025From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMscited by 12
  22. 2021Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performancecited by 10
  23. 2023Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?cited by 8
  24. 2023Can LLMs Capture Human Preferences?cited by 6
  25. 2024DelayPTC-LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Modelscited by 6
  26. 2019Rethinking travel behavior modeling representations through embeddingscited by 5
  27. 2023Attitudes and Latent Class Choice Models using Machine learningcited by 2
  28. 2023Incorporating Domain Knowledge in Deep Neural Networks for Discrete Choice Modelscited by 2
  29. 2025Incorporating graph neural network into route choice modelcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understandingcited by 20
  2. 2025LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMscited by 2
  3. 2025LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modelingcited by 2
  4. 2025Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviourcited by 1
  5. 2026AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?cited by 0
  6. 2026An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Predictioncited by 0
  7. 2026Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024AI-Driven Day-to-Day Route Choice
  2. 2025Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?
  3. 2025Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
  4. 2024Towards a Unified View of Preference Learning for Large Language Models: A Survey
  5. 2024A Survey on Human Preference Learning for Large Language Models
  6. 2025Benchmarking Retrieval-Augmented Generation Strategies for Large Language Model-Based Travel Mode Choice Prediction
  7. 2024Using LLMs to Model the Beliefs and Preferences of Targeted Populations
  8. 2026Evaluating LLM-Generated Preference Distributions