Related papers: Synthia: Scalable Grounded Persona Generation from…
Large language models (LLMs) have great potential for synthetic data generation. This work shows that useful data can be synthetically generated even for tasks that cannot be solved directly by LLMs: for problems with structured outputs, it…
This paper examines biases in large language models (LLMs) when generating synthetic populations from responses to personality questionnaires. Using five LLMs, we first assess the representativeness and potential biases in the…
Large Language Models (LLMs) offer new avenues to simulate online communities and social media. Potential applications range from testing the design of content recommendation algorithms to estimating the effects of content policies and…
Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as…
This position paper explores the benefits, drawbacks, and ethical considerations of incorporating synthetic personae in HCI research, particularly focusing on the customization challenges beyond the limitations of current Large Language…
Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction…
This paper introduces PersonaAI, a cutting-edge application that leverages Retrieval-Augmented Generation (RAG) and the LLAMA model to create highly personalized digital avatars capable of accurately mimicking individual personalities.…
As large language models (LLMs) advance, their ability to perform in-context learning and few-shot language generation has improved significantly. This has spurred using LLMs to produce high-quality synthetic data to enhance the performance…
A central challenge in social science is to generate rich qualitative hypotheses about how diverse social groups might interpret new information. This article introduces and illustrates a novel methodological approach for this purpose:…
Static benchmarks for harmful content detection face limitations in scalability and diversity, and may also be affected by contamination from web-scale pre-training corpora. To address these issues, we propose a framework for synthesizing…
Since the COVID-19 pandemic, clinicians have seen a large and sustained influx in patient portal messages, significantly contributing to clinician burnout. To the best of our knowledge, there are no large-scale public patient portal…
Generating social networks is essential for many applications, such as epidemic modeling and social simulations. The emergence of generative AI, especially large language models (LLMs), offers new possibilities for social network…
Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as…
Networked environments shape how information embedded in narratives influences individual and group beliefs and behavior. This raises key questions about how group communication around narrative media impacts belief formation and how such…
Generative AI (GenAI) is increasingly used in survey contexts to simulate human preferences. While many research endeavors evaluate the quality of synthetic GenAI data by comparing model-generated responses to gold-standard survey results,…
In many simulation studies involving networks there is the need to rely on a sample network to perform the simulation experiments. In many cases, real network data is not available due to privacy concerns. In that case we can recourse to…
While LLMs have demonstrated remarkable capabilities in text generation and reasoning, their ability to simulate human decision-making -- particularly in political contexts -- remains an open question. However, modeling voter behavior…
We introduce a constraint-programming framework for generating synthetic populations that reproduce target statistics with high precision while enforcing full individual consistency. Unlike data-driven approaches that infer distributions…
The scarcity of domain-specific dialogue datasets limits the development of dialogue systems across applications. Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. To…
Generative agent simulations operate at two scales: individual personas for character interaction, and population models for collective behavior analysis and intervention testing. We propose a third scale: meso-level simulation -…