Webb, Holyoak & Lu (2023) compared human reasoners and GPT-3 on several tasks involving analogy resolution, documenting human-level or superhuman performance in most conditions. In this direct replication, we tested a different, open-weights language model (Mixtral-8x7B) on the same materials...

Die Erstellung eines Intelligence Collection Plans (ICP) stellt einen zentralen Arbeitsschritt im Schnittpunkt aus der Direction-Phase (siehe Abbildung 1) und dem Intelligence Requirement Management (IRM) innerhalb des Intelligence Cycle dar. Dieser soll ermöglichen, Informationsbedarfe...

In many jurisdictions, academia is at the service of legal practice. Law professors write commentaries that summarize the state of the art of doctrine, chiefly of jurisprudence. In the spirit of a proof of concept, using the guarantee of freedom of assembly in the European Convention on Human...

This article develops a novel economic sentiment indicator (LLM-ESI) by applying large language models to open-ended responses from Swiss business tendency surveys. Using a BERT-based transformer model, it extracts firmlevel sentiment from free-text survey comments and aggregates it into a...

Complex problems such as climate change pose severe challenges to societies worldwide. To overcome these challenges, digital innovation contests have emerged as a promising tool for idea generation. However, assessing idea quality in innovation contests is becoming increasingly problematic in...

Geoeconomic pressure--the use of existing economic relationships by governments to achieve geopolitical or economic goals--is a prominent feature of global power dynamics. This paper introduces a methodology using large language models (LLMs) to systematically identify the application of and...

How can we use the novel capacities of large language models (LLMs) in empirical research? And how can we do so while accounting for their limitations, which are themselves only poorly understood? We develop an econometric framework to answer this question that distinguishes between two types of...

"Book Summary: This book is tailored for students, traders, and quants in finance who want to understand modern trading strategies and enhance them with artificial intelligence. It assumes basic knowledge of Python 3.x and familiarity with finance and trading concepts. Goals: AI Overview:...

In the immersive complexity of digital innovation, data-driven solution design often begins with a specific technology or potential solution already in mind. However, this predisposition narrows the design space and reduces the probability of discovering more suitable or novel alternatives. This...

We propose a new LLM-based survey framework that enables retrospective coverage, economic reasoning, dynamic effects, and clean identification. We recover human-comparable treatment effects in a multi-wave randomized controlled trial of inflation expectations surveys, at 1/1000 the cost. To...

Die Anamneseerhebung ist eine wesentliche Fertigkeit in allen Gesundheitsberufen. Die Ausbildung in dieser Fähigkeit im Rahmen eines Studiums ist jedoch mit zahlreichen Hürden verbunden. Virtuelle Patient:innen, mit denen Gespräche auf der Grundlage von "Large Language Models" (LLM) geführt...

We study the evolution of patenting in China from 1985-2019. We use a Large Language Model to measure patent importance based on patent abstracts and classify patent ownership using a comprehensive business registry. We highlight four insights. First, average patent importance declined from...

Independent and high-quality evaluations of government policies are an important input for designing evidence-based policy. Lack of incentives and institutions to write such evaluations, on the other hand, carry the risk of turning the system into a costly beauty contest. We study one of the...

In an experiment on the large language model GPT-4o, a supplier always makes a higher profit if it replaces uniform contract terms with a set of terms between which the customer may choose. The extra profit results from price discrimination. There is a first order and a second order effect. The...

Macro-task crowdsourcing presents a promising approach to address wicked problems like climate change by leveraging the collective efforts of a diverse crowd. Such macro-task crowdsourcing requires facilitation. However, in the facilitation process, traditionally aggregating and synthesizing...

ChatGPT frequently appears in the media, with many predicting significant disruptions, especially in the fields of accounting and auditing. Yet research has demonstrated relatively poor performance of ChatGPT on student assessment questions. We extend this research to examine whether more recent...

Seit seiner Veröffentlichung gewinnt das Large Language Model (Großes Sprachmodell) ChatGPT zunehmend an Bedeutung in der deutschen Bildungslandschaft. Während Schülerinnen und Schüler dieses Large Language Model bereits aktiv nutzen, herrscht unter Lehrkräften noch Uneinigkeit darüber,...

Diversity-Programme verfolgen nicht nur das Ziel, wirtschaftliche Potenziale zu erschließen, sondern auch, die Entwicklung von Unternehmen hin zu einer zeitgemäßen und ethisch vertretbaren Unternehmenskultur zu fördern. Trotz der positiven Absichten der Unternehmen, Diversity-Programme...

Independent and high-quality evaluations of government policies are an important input for designing evidence-based policy. Institutional frictions and lack of incentives to write such evaluations, on the other hand, carry the risk of turning the system into a costly beauty contest. We study one...

We study the evolution of patenting in China from 1985-2019. We use a Large Language Model to measure patent importance based on patent abstracts and classify patent ownership using a comprehensive business registry. We highlight four insights. First, average patent importance declined from...

In an experiment on the large language model GPT-4o, a supplier always makes a higher profit if it replaces uniform contract terms with a set of terms between which the customer may choose. The extra profit results from price discrimination. There is a first order and a second order effect. The...

Die Anamneseerhebung ist eine wesentliche Fertigkeit in allen Gesundheitsberufen. Die Ausbildung in dieser Fähigkeit im Rahmen eines Studiums ist jedoch mit zahlreichen Hürden verbunden. Virtuelle Patient:innen, mit denen Gespräche auf der Grundlage von "Large Language Models" (LLM) geführt...

We study the evolution of patenting in China from 1985-2019. We use a Large Language Model to measure patent importance based on patent abstracts and classify patent ownership using a comprehensive business registry. We highlight four insights. First, average patent importance declined from...

Independent and high-quality evaluations of government policies are an important input for designing evidence-based policy. Lack of incentives and institutions to write such evaluations, on the other hand, carry the risk of turning the system into a costly beauty contest. We study one of the...