mlsanityData to 14 Oct 2026

Large Language Models for Market Research: A Data-augmentation Approach

arXiv 2412.19363 ↗First posted 26 Dec 2024cs.AI cs.LG stat.MEcited by 20

On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation

Abstract (arXiv)

Large Language Models (LLMs) have transformed artificial intelligence by excelling in complex natural language processing tasks. Their ability to generate human-like text has opened new possibilities for market research, particularly in conjoint analysis, where understanding consumer preferences is essential but often resource-intensive. Traditional survey-based methods face limitations in scalability and cost, making LLM-generated data a promising alternative. However, while LLMs have the potential to simulate real consumer behavior, recent studies highlight a significant gap between LLM-generated and human data, with biases introduced when substituting between the two. In this paper, we address this gap by proposing a novel statistical data augmentation approach that efficiently integrates LLM-generated data with real data in conjoint analysis. This results in statistically robust estimators with consistent and asymptotically normal properties, in contrast to naive approaches that simply substitute human data with LLM-generated data, which can exacerbate bias. We further present a finite-sample performance bound on the estimation error. We validate our framework through an empirical study on COVID-19 vaccine preferences, demonstrating its superior ability to reduce estimation error and save data and costs by 24.9% to 79.8%. In contrast, naive approaches fail to save data due to the inherent biases in LLM-generated data compared to human data. Another empirical study on sports car choices validates the robustness of our results. Our findings suggest that while LLM-generated data is not a direct substitute for human responses, it can serve as a valuable complement when used within a robust statistical framework.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 11 of its 37 references that are in the map. First posted on arXiv 26 Dec 2024.

Builds on

11 of 37 references.

References · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  7. 2024The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunitiescited by 64
  8. 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspectivecited by 59
  9. 2024Large Language Models: An Applied Econometric Frameworkcited by 32
  10. 2024Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?cited by 26
  11. 2024Are Large Language Models (LLMs) Good Social Predictors?cited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 15.

20 papers.

Sort:

By area:

  1. 2025What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commercecited by 22
  2. 2025Auto-Formulating Dynamic Programming Problems with Large Language Modelscited by 16
  3. 2025Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributionscited by 5
  4. 2026LLM-SAA: LLM-persona Generated Distributions for Decision-makingcited by 3
  5. 2025Robustness is Important: Limitations of LLMs for Data Fittingcited by 2
  6. 2025Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Managementcited by 2
  7. 2026Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidencecited by 2
  8. 2026Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?cited by 2
  9. 2026Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issuescited by 1
  10. 2026When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutabilitycited by 1
  11. 2026Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigationcited by 0
  12. 2026LIBRA: Language Model Informed Bandit Recourse Algorithm for Personalized Treatment Planningcited by 0
8 more
  1. 2026AI-Generated Measurements for Identification and Inference with Missing Data: A Weak Shadow Variable Approachcited by 0
  2. 2026Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveyscited by 0
  3. 2026LLM Biasescited by 0
  4. 2026LLM-Powered Virtual Population for Demand Simulation and Pricingcited by 0
  5. 2026SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluationcited by 0
  6. 2026Learning a Size-Weight Frontier for Synthetic-Augmented Inferencecited by 0
  7. 2026Distributional Validity of a Korean Synthetic Persona Panel: Evidence From the Korea Media Panel Surveycited by 0
  8. 2026PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025An Overview of Large Language Models for Statisticians
  2. 2025Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective
  3. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges
  4. 2026Evaluating LLM-Generated Preference Distributions
  5. 2024A Survey on Data Synthesis and Augmentation for Large Language Models
  6. 2024Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized Evaluation
  7. 2025Do Large Language Models (Really) Need Statistical Foundations?
  8. 2024Using LLMs to Model the Beliefs and Preferences of Targeted Populations