# LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings

arXiv: https://arxiv.org/abs/2510.08338 · HTML: https://mlsanity.com/paper/2510.08338/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Large Language Models Show Human-like Social Desirability Biases in Survey Responses](https://mlsanity.com/paper/2405.06058/) (2024)

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

- [Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data](https://mlsanity.com/paper/2606.28963/) (2026)
- [Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench](https://mlsanity.com/paper/2605.17079/) (2026)
- [Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates](https://mlsanity.com/paper/2608.29455/) (2026)
- [Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation](https://mlsanity.com/paper/2602.18891/) (2026)
- [Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys](https://mlsanity.com/paper/2604.17267/) (2026)
- [CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session Recordings](https://mlsanity.com/paper/2605.17370/) (2026)
- [Reason-Mediated Behavioral Models for Auditing LLM Social Simulators](https://mlsanity.com/paper/2607.24649/) (2026)
- [Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic Experimentation](https://mlsanity.com/paper/2608.02345/) (2026)
- [Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format](https://mlsanity.com/paper/2609.09882/) (2026)
- [Agent-based Modeling: Equilibrium, Echo Chambers, and Efficiency in Hybrid Coevolutionary Opinion Games](https://mlsanity.com/paper/2609.27639/) (2026)
- [RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations](https://mlsanity.com/paper/2610.01780/) (2026)
- [Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents](https://mlsanity.com/paper/2610.14912/) (2026)

## Abstract (arXiv)

Consumer research costs companies billions annually yet suffers from panel biases and limited scale. Large language models (LLMs) offer an alternative by simulating synthetic consumers, but produce unrealistic response distributions when asked directly for numerical ratings. We present semantic similarity rating (SSR), a method that elicits textual responses from LLMs and maps these to Likert distributions using embedding similarity to reference statements. Testing on an extensive dataset comprising 57 personal care product surveys conducted by a leading corporation in that market (9,300 human responses), SSR achieves 90% of human test-retest reliability while maintaining realistic response distributions (KS similarity > 0.85). Additionally, these synthetic respondents provide rich qualitative feedback explaining their ratings. This framework enables scalable consumer research simulations while preserving traditional survey metrics and interpretability.