top of page
Research
In this section, we showcase the most recent research findings here.
USING LARGE LANGUAGE MODELS FOR SHORT TEXT TOPIC MODELING: MODEL CHOICE AND SAMPLE SIZE
Imagine you're trying to organize thousands of comments about a product into main themes or topics. Traditionally, researchers either had...
New GenAI Framework for Generating and Evaluating Scientific Hypotheses
Imagine if we could automate the discovery of groundbreaking scientific hypotheses, unlocking new possibilities faster than ever before....
AI's Peer Review: GPT-4 Matches Human Experts in Scientific Feedback
This article, titled "Can Large Language Models Provide Useful Feedback on Research Papers? A Large-Scale Empirical Analysis", is a...
Researchers Find AI Chatbot GPT Effective for Multilingual Psychological Text Analysis
A new study published in the Proceedings of the National Academy of Sciences finds that the artificial intelligence chatbot GPT is an...
Generative AI for Economic Research: Use Cases and Implications for Economists
Anton Korinek, JOURNAL OF ECONOMIC LITERATURE The landscape of generative artificial intelligence (AI) has seen rapid evolution,...
PNAS: Can Generative AI improve social science?
Christopher A. Baila, aDepartment of Sociology, Duke University https://doi.org/10.1073/pnas.2314021121 This perspective article by...
Sentiment Analysis in the Age of Generative AI
Jan Ole Krugmann & Jochen Hartmann Abstract In the rapidly advancing age of Generative AI, Large Language Models (LLMs) such as ChatGPT...
Determining the Validity of Large Language Models for Automated Perceptual Analysis
Peiyao Li, Noah Castelo, Zsolt Katona, Miklos Sarvary Published Online:25 Jan 2024 https://doi.org/10.1287/mksc.2023.0454 Abstract: This...
Is it ok to use LLMs in peer review?
A study of review reports identifies dozens of adjectives that could indicate text written with the help of chatbots. A study [preprint,...
Systematic testing of three Language Models reveals low language accuracy, absence of response stability, and a yes-response bias
Vittoria Dentella https://orcid.org/0000-0001-6697-9184 vittoria.dentella@urv.cat, Fritz Günther https://orcid.org/0000-0002-9205-6786,...
ChatGPT outperforms crowd workers for text-annotation tasks
Fabrizio Gilardi https://orcid.org/0000-0002-0635-3048 gilardi@ipz.uzh.ch, Meysam Alizadeh https://orcid.org/0000-0001-6696-6471, and...
Large language models show human-like content biases in transmission chain experiments
Alberto Acerbi https://orcid.org/0000-0001-5827-8003 alberto.acerbi@unitn.it and Joseph M. Stubbersfield https://orcid.org/0000-0001-8966...
Uncovering the semantics of concepts using GPT-4
Gaël Le Mens https://orcid.org/0000-0003-4800-0598 gael.le-mens@upf.edu, Balázs Kovács https://orcid.org/0000-0001-6916-6357, Michael T....
bottom of page