21 Peer reviewed papers that support the Synthetic Users thesis
Here is a compilation of all the papers that help make a case for Synthetic Users.
In the rapidly evolving landscape of AI and user research, it's natural—and indeed, healthy—to approach new technologies with a degree of skepticism. At Synthetic Users, we not only understand this skepticism but welcome it as an opportunity to showcase the solid scientific foundation upon which our technology is built.
Spoiler Link to page with all the papers: Research Papers Supporting Synthetic Users
Rooted in Reality, Not Science Fiction
Contrary to what some might assume, Synthetic Users aren't conjured out of thin air or based on speculative algorithms. They are meticulously reconstructed from the vast ocean of publicly available data that we, as organic users, have been creating for decades. This data forms the bedrock of our synthetic user profiles, ensuring that they reflect real-world behaviors, preferences, and thought patterns.
The Power of Collective Digital Footprints
Think of Synthetic Users as a sophisticated mosaic, each piece carefully selected from the collective digital footprint of humanity. Social media posts, online reviews, forum discussions, and public datasets all contribute to this rich tapestry of human behavior. By leveraging advanced machine learning techniques, we distill this raw data into coherent, realistic user profiles that can accelerate and enhance user and market research.
Advancing the Field Through Rigorous Research
We have the utmost respect for researchers who are continuously exploring this new frontier where Large Language Models (LLMs) and Agent architectures can simulate organic users with a high degree of parity. After all, we're dealing with synthetic neural network architectures modeled after us, organic users. This symbiosis between artificial and human intelligence is not just fascinating—it's the key to unlocking new insights in user research.
To underscore the credibility of Synthetic Users as accelerators of user and market research, we've compiled a list of peer-reviewed papers and studies that lend substantial credence to the efficacy and reliability of our approach. Here are some key research papers that form the foundation of our technology:
Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus? - This paper explores the potential of using large language models to simulate economic agents, providing insights into human behavior and decision-making processes.
Human-like Decision-making AI Agent with Large Language Model and Reinforcement Learning - This study demonstrates how combining large language models with reinforcement learning can create AI agents capable of human-like decision-making, a crucial aspect of Synthetic Users.
Generative Agents: Interactive Simulacra of Human Behavior - This research introduces generative agents as interactive simulacra of human behavior, closely aligning with the concept of Synthetic Users.
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models - While not directly related to Synthetic Users, this paper showcases the potential of AI models to engage in multi-modal interactions, which could enhance the realism of synthetic user interactions in the future.
Voyager: An Open-Ended Embodied Agent with Large Language Models - This paper presents an AI agent capable of open-ended learning and interaction, demonstrating the potential for creating more dynamic and adaptable Synthetic Users.
These papers represent just a fraction of the ongoing research in this field. We encourage you to explore these studies and the many others listed on our Research Papers Supporting Synthetic Users page.
Releated Articles
More articles for you
Teaching Synthetic Users What Real People Actually Think
Synthetic Users without calibration are individually believable, but collectively wrong. The missing piece is calibration, not better models.
The Lie We Tell Ourselves About Customer Research
Most research asks what people say. The problem is people don't do what they say. This piece breaks down the gap between stated and revealed preference — and why behavioral modeling, not better interviews, is how you close it.
Two ways to run research with Synthetic Users and why the difference matters
Iris, what is the difference of using agents to accelerate research.
Synthetic Users vs digital twins
You don’t need a twin for “a parent in rural Ohio who shops weekly at Walmart, prefers fragrance-free, and has a toddler with eczema.” You sample a parent profile with relevant traits and constraints, add retail and dermatology context, and generate behaviors consistent with both.
Two major papers. One shared direction.
LLM-powered Synthetic Users have crossed from concept to validated method. This proves they can predict human behavior accurately, letting teams run fast, low-cost behavioral experiments without replacing real participants.
Gartner says we lead. That's kind of them.
Gartner’s latest report on AI-powered synthetic user research cites Synthetic Users as a leader.
Introducing Shuffle v2
Shuffle v2 is a feature that intelligently shuffles between multiple large language models via a routing agent to produce more realistic, diverse Synthetic Users with better organic parity.
Chain-of-feeling
Synthetic Users use a “chain-of-feeling” approach—combining emotional states with OCEAN personality traits—to produce more human-like, realistic user responses and yield richer UX insights.
Generative Agent Simulations of 1,000 People
A paper that thoroughly executes a parity study between Synthetic and Organic users.
21 Peer reviewed papers that support the Synthetic Users thesis
Here is a compilation of all the papers that help make a case for Synthetic Users.
Why we shuffle between models — to ensure both parity and diversity!
Synthetic Users balances aligned and unaligned models to maintain diversity and authenticity in simulated users while ensuring ethical standards and user expectations are met.
Latest press articles for Synthetic Users
Synthetic Users and AI are transforming research methodologies, offering innovative, cost-effective alternatives to traditional human subject studies.
Comparison studies. The opportunity lies in the deviation.
When we compare different studies, especially looking at what synthetic (artificial interviews) and organic (real-world interviews) data tell us, we often find they mostly talk about the same things but there's also a bit where they don't match up. This gap is super interesting because it's like finding hidden treasure in what we thought we knew versus what we might have missed.
How we deal with bias
Harnessing the power of AI in our Synthetic Users, we strive for a balance between reflecting reality and ethical responsibility, ensuring diversity and fairness while maintaining realism.
The transition to Continuous Insight
The transition towards Continuous Insight™ aligns research activities more closely with the dynamic needs of the business and ensures that product development is continuously informed by up-to-date user insights.
The Art of the Vibes Engine
Large language models (LLMs) like GPT-4 serve as powerful "vibes engines," empathizing with diverse groups and generating contextually relevant content. Their applications span market research, customer support, user experience design, and mental health support, offering invaluable insights and personalized experiences. While not infallible sources of truth, LLMs enable creativity, personalization, and connection within the realm of human language.
There is a faster and more accurate way to do research. Use Synthetic Users.
How Synthetic Users is changing the research process.
The wisdom of the silicon crowd
In the light of an ancient parable, we explore a new paper that dives into how ensembles of large language models match the prediction accuracy of human crowds. It reveals that combining machine predictions with human insights leads to the most robust forecasting results.
Three research papers that helped us build ❤️ Synthetic Users
For the sceptics amongst us who need more tangible research in order to engage with this brave new world. Full disclosure: we are part of the sceptics.
What is RAG and why it’s important for Synthetic Research
Ahead of our RAG launch we explain Retrieval-Augmented Generation (RAG) and how it enhances Synthetic Users by providing increased realism, contextual depth, and adaptive learning, with profound implications for market research, user experience testing, training, education, and innovative product development.
Synthetic Users system architecture (the simplified version).
Foundation models underpin Synthetic Users with advanced capabilities, enhanced by synthetic data and RAG layers for realism and business alignment, all within a collaborative multi-agent framework for richer interactions.
Saturation score. How do we know how many interviews to run?
Determine your interview target for achieving topic saturation using our efficient approach, leveraging the historical wisdom of research pioneers. This method ensures deep insights with theoretical sampling at its core.
How Synthetic Users are gaining depth
Synthetic Users are evolving to address criticism about their generalist nature by incorporating representative data sets and personal narratives.
How we compare interviews to ensure we improve our Synthetic Organic Parity — 85 to 92%
How do we know we are right? How do we know our Synthetic Users are as real as organic users? We compare.
Synthetic Users: Merging Qualitative and Quantitative Research, in seconds.
At Synthetic users we are blurring the lines between qualitative and quantitative research. Here's how we are going about this transformative approach.