Morteza Dehghani
@mdehghani.bsky.social
Professor of Psychology and Computer Science at USC
At @spspnews.bsky.social, many asked for guidelines on using LLMs in the social sciences. Our new paper in AMPPS addresses exactly that! We provide a primer for evaluating LLMs in social science research, focusing on methodological rigor, replicability, and validity: osf.io/preprints/ps...
February 25, 2025 at 11:01 PM
At @spspnews.bsky.social, many asked for guidelines on using LLMs in the social sciences. Our new paper in AMPPS addresses exactly that! We provide a primer for evaluating LLMs in social science research, focusing on methodological rigor, replicability, and validity: osf.io/preprints/ps...
Our new paper explores how to align LLMs with System 1 (intuitive) and System 2 (analytical) thinking styles. This work challenges the idea that step-by-step reasoning (CoT) is always best and highlights the need for adapting reasoning strategies based on the task
arxiv.org/abs/2502.12470
arxiv.org/abs/2502.12470
February 19, 2025 at 10:00 PM
Our new paper explores how to align LLMs with System 1 (intuitive) and System 2 (analytical) thinking styles. This work challenges the idea that step-by-step reasoning (CoT) is always best and highlights the need for adapting reasoning strategies based on the task
arxiv.org/abs/2502.12470
arxiv.org/abs/2502.12470
Our new paper explores how to align LLMs with System 1 (intuitive) and System 2 (analytical) thinking styles. This work challenges the idea that step-by-step reasoning (CoT) is always best and highlights the need for adapting reasoning strategies based on the task
arxiv.org/abs/2502.12470
arxiv.org/abs/2502.12470
February 19, 2025 at 9:59 PM
Our new paper explores how to align LLMs with System 1 (intuitive) and System 2 (analytical) thinking styles. This work challenges the idea that step-by-step reasoning (CoT) is always best and highlights the need for adapting reasoning strategies based on the task
arxiv.org/abs/2502.12470
arxiv.org/abs/2502.12470