Philipp Schoenegger
YOU?
Author Swipe
View article: Prompt Engineering Large Language Models' Forecasting Capabilities
Prompt Engineering Large Language Models' Forecasting Capabilities Open
Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often wor…
View article: Large Language Models Are More Persuasive Than Incentivized Human Persuaders
Large Language Models Are More Persuasive Than Incentivized Human Persuaders Open
We directly compare the persuasion capabilities of a frontier large language model (LLM; Claude Sonnet 3.5) against incentivized human persuaders in an interactive, real-time conversational quiz setting. In this preregistered, large-scale …
View article: AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy
AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy Open
Large language models (LLMs) match and sometimes exceed human performance in many domains. This study explores the potential of LLMs to augment human judgment in a forecasting task. We evaluate the effect on human forecasters of two LLM as…
View article: Wisdom of the silicon crowd: LLM ensemble prediction capabilities rival human crowd accuracy
Wisdom of the silicon crowd: LLM ensemble prediction capabilities rival human crowd accuracy Open
Human forecasting accuracy improves through the “wisdom of the crowd” effect, in which aggregated predictions tend to outperform individual ones. Past research suggests that individual large language models (LLMs) tend to underperform comp…
View article: Correction: Sure-thing vs. probabilistic charitable giving: Experimental evidence on the role of individual differences in risky and ambiguous charitable decision-making
Correction: Sure-thing vs. probabilistic charitable giving: Experimental evidence on the role of individual differences in risky and ambiguous charitable decision-making Open
[This corrects the article DOI: 10.1371/journal.pone.0273971.].
View article: Can AI Understand Human Personality? -- Comparing Human Experts and AI Systems at Predicting Personality Correlations
Can AI Understand Human Personality? -- Comparing Human Experts and AI Systems at Predicting Personality Correlations Open
We test the abilities of specialised deep neural networks like PersonalityMap as well as general LLMs like GPT-4o and Claude 3 Opus in understanding human personality. Specifically, we compare their ability to predict correlations between …
View article: Scientific realism, scientific practice, and science communication: An empirical investigation of academics and science communicators
Scientific realism, scientific practice, and science communication: An empirical investigation of academics and science communicators Open
We argue that the societal consequences of the scientific realism debate, in the context of science-to-public communication are often overlooked and careful theorizing about it needs further empirical groundwork. As such, we conducted a su…
View article: Moral hazards and solar radiation management: Evidence from a large-scale online experiment
Moral hazards and solar radiation management: Evidence from a large-scale online experiment Open
Solar radiation management (SRM) may help to reduce the negative outcomes of climate change by minimising or reversing global warming. However, many express the worry that SRM may pose a moral hazard, i.e., that information about SRM may l…
View article: Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy
Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy Open
Human forecasting accuracy in practice relies on the 'wisdom of the crowd' effect, in which predictions about future events are significantly improved by aggregating across a crowd of individual forecasters. Past work on the forecasting ab…
View article: AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy
AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy Open
Large language models (LLMs) match and sometimes exceeding human performance in many domains. This study explores the potential of LLMs to augment human judgement in a forecasting task. We evaluate the effect on human forecasters of two LL…
View article: Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament
Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament Open
Accurately predicting the future would be an important milestone in the capabilities of artificial intelligence. However, research on the ability of large language models to provide probabilistic predictions about future events remains nas…
View article: Moral Hazards and Geoengineering: Evidence from a Large-Scale Online Experiment
Moral Hazards and Geoengineering: Evidence from a Large-Scale Online Experiment Open
Geoengineering (especially solar radiation management) may helpto reduce the negative outcomes of climate change by minimising orreversing global warming. However, many express the worry thatgeoengineering may pose a moral hazard, i.e., th…
View article: Introduction and Validation of the Short Antinatalism Scale (S-ANS)
Introduction and Validation of the Short Antinatalism Scale (S-ANS) Open
Antinatalism is the view that procreation is morally wrong. This paper introduces and validates the Short Antinatalism Scale (S-ANS) that allows researchers to measure antinatalist views. We conducted four preregistered studies with a tota…
View article: Diminished Diversity-of-Thought in a Standard Large Language Model
Diminished Diversity-of-Thought in a Standard Large Language Model Open
We test whether Large Language Models (LLMs) can be used to simulate human participants in social-science studies. To do this, we run replications of 14 studies from the Many Labs 2 replication project with OpenAI's text-davinci-003 model,…
View article: Sure-thing vs. probabilistic charitable giving: Experimental evidence on the role of individual differences in risky and ambiguous charitable decision-making
Sure-thing vs. probabilistic charitable giving: Experimental evidence on the role of individual differences in risky and ambiguous charitable decision-making Open
Charities differ, among other things, alongside the likelihood that their interventions succeed and produce the desired outcomes and alongside the extent that such likelihood can even be articulated numerically. In this paper, we investiga…
View article: Causal and Associational Language in Observational Health Research: A Systematic Evaluation
Causal and Associational Language in Observational Health Research: A Systematic Evaluation Open
We estimated the degree to which language used in the high-profile medical/public health/epidemiology literature implied causality using language linking exposures to outcomes and action recommendations; examined disconnects between langua…
View article: Taking a Closer Look at the Bayesian Truth Serum
Taking a Closer Look at the Bayesian Truth Serum Open
Over the past few decades, psychology and its cognate disciplines have undergone substantial scientific reform, ranging from advances in statistical methodology to significant changes in academic norms. One aspect of experimental design th…
View article: Causal and Associational Language in Observational Health Research: A systematic evaluation
Causal and Associational Language in Observational Health Research: A systematic evaluation Open
We estimated the degree to which language used in the high profile medical/public health/epidemiology literature implied causality using language linking exposures to outcomes and action recommendations; examined disconnects between langua…
View article: On the Epistemological Similarities of Market Liberalism and Standpoint Theory
On the Epistemological Similarities of Market Liberalism and Standpoint Theory Open
In this paper, we draw attention to the epistemological assumptions of market liberalism and standpoint theory and argue that they have more in common than previously thought. We show that both traditions draw on a similar epistemological …