Skip to main navigation Skip to main content
info(at)avldigital.remove-this.de
Deutsch English
Last searches

Results for *

Displaying results 1 to 14 of 14.

  1. Quality and accountability of Large Language Models (LLMs) in healthcare in low- and middle-income countries (LMIC)
    a simulated patient study using ChatGPT
    Author: Si, Yafei; Yang, Yuji; Wang, Xi; An, Ruopeng; Zu, Jiaqi; Chen, Xi; Fan, Xiaojing; Gong, Sen
    Published: August 2024
    Publisher:  IZA - Institute of Labor Economics, Bonn, Germany

    Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find... more

    Access:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 4
    Inter-library loan:
    No inter-library loan

     

    Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find ChatGPT's performance varied within a single disease, despite a high level of accuracy in both correct diagnosis (74.1%) and medication prescription (84.5%). Additionally, ChatGPT recommended a concerning level of unnecessary or harmful medications (85.2%) even with correct diagnoses. Finally, ChatGPT performed better in managing non-communicable diseases compared to infectious ones. These results highlight the need for cautious AI integration in healthcare systems to ensure quality and safety.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/305646
    Series: Discussion paper series / IZA ; no. 17204
    Subjects: ChatGPT; Large Language Models; generative AI; simulated patient; healthcare; quality; safety; low- and middle-income countries
    Scope: 1 Online-Ressource (circa 11 Seiten), Illustrationen
  2. Battle of transformers
    adversarial attacks on financial sentiment models
    Author: Turetken, Aysun Can; Leippold, Markus
    Published: [2024]
    Publisher:  Swiss Finance Institute, Geneva

    Access:
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    Keine Rechte
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    Series: Swiss Finance Institute research paper series ; no 24, 59
    Subjects: Adversarial Attacks; Large Language Models; Financial Sentiment Analysis
    Scope: 1 Online-Ressource (circa 36 Seiten), Illustrationen
  3. Quantifying uncertainty
    a new era of measurement through large language models
    Author: Audrino, Francesco; Gentner, Jessica; Stalder, Simon
    Published: [2024]
    Publisher:  Swiss Finance Institute, Geneva

    Access:
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    Keine Rechte
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    Series: Swiss Finance Institute research paper series ; no 24, 68
    Subjects: Uncertainty measurement; Large Language Models; Economic policy; Geopolitical risk; Monetary policy; Financial markets
    Scope: 1 Online-Ressource (circa 56 Seiten), Illustrationen
  4. AI-generated production networks
    measurement and applications to global trade
    Author: Fetzer, Thiemo; Lambert, Peter; Feld, Bennet; Garg, Prashant
    Published: November 2024
    Publisher:  ECONtribute, [Bonn]

    This paper leverages generative AI to build a network structure over 5,000 product nodes, where directed edges represent input-output relationships in production. We layout a two-step 'build-prune' approach using an ensemble of prompt-tuned... more

    Access:
    Verlag (kostenfrei)
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 711
    Inter-library loan:
    No inter-library loan

     

    This paper leverages generative AI to build a network structure over 5,000 product nodes, where directed edges represent input-output relationships in production. We layout a two-step 'build-prune' approach using an ensemble of prompt-tuned generative AI classifications. The 'build' step provides an initial distribution of edgepredictions, the 'prune' step then re-evaluates all edges. With our AI-generated Production Network (AIPNET) in toe, we document a host of shifts in the network position of products and countries during the 21st century. Finally, we study production network spillovers using the natural experiment presented by the 2017 blockade of Qatar. We find strong evidence of such spill-overs, suggestive of on-shoring of critical production. This descriptive and causal evidence demonstrates some of the many research possibilities opened up by our granular measurement of product linkages, including studies of on-shoring, industrial policy, and other recent shifts in global trade

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/307310
    Series: ECONtribute discussion paper ; no. 346
    Subjects: Supply-Chain Network Analysis; Large Language Models; On-shoring; industrial policy; Trade wars; Econometrics-of-LLMs
    Scope: 1 Online-Ressource (circa 107 Seiten), Illustrationen
  5. We need to talk
    audio surveys and information extraction
    Author: Galasso, Vincenzo; Nannicini, Tommaso; Nozza, Debora
    Published: November 2024
    Publisher:  CESifo, Munich, Germany

    Understanding individuals’ beliefs, preferences, and motivations is essential in social sciences. Recent technological advancements—notably, large language models (LLMs) for analyzing open-ended responses and the diffusion of voice messaging—have the... more

    Access:
    Verlag (kostenfrei)
    Verlag (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 63
    Inter-library loan:
    No inter-library loan

     

    Understanding individuals’ beliefs, preferences, and motivations is essential in social sciences. Recent technological advancements—notably, large language models (LLMs) for analyzing open-ended responses and the diffusion of voice messaging—have the potential to significantly enhance our ability to elicit these dimensions. This study investigates the differences between oral and written responses to open-ended survey questions. Through a series of randomized controlled trials across three surveys (focused on AI, public policy, and international relations), we assigned respondents to answer either by audio or text. Respondents who provided audio answers gave longer, though lexically simpler, responses compared to those who typed. By leveraging LLMs, we evaluated answer informativeness and found that oral responses differ in both quantity and quality, offering more information and containing more personal experiences than written responses. These findings suggest that oral responses to open-ended questions can capture richer, more personal insights, presenting a valuable method for understanding individual reasoning.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Series: CESifo working papers ; 11530 (2024)
    Subjects: survey design; open-ended questions; Large Language Models; beliefs
    Scope: 1 Online-Ressource (circa 52 Seiten)
  6. Large language models in economics
    Author: Ash, Elliott; Hansen, Stephen; Muvdi, Yabra
    Published: 13 September 2024
    Publisher:  Centre for Economic Policy Research, London

    Access:
    Verlag (Deutschlandweit zugänglich)
    Verlag (Deutschlandweit zugänglich)

    Location:
    Staatsbibliothek zu Berlin - Preußischer Kulturbesitz, Haus Potsdamer Straße
    Inter-library loan:
    No inter-library loan

    Location:
    Universitätsbibliothek Freiburg
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Inter-library loan:
    No inter-library loan

    Location:
    Universität Potsdam, Universitätsbibliothek
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Staatsbibliothek zu Berlin
    Language: English
    Media type: Book
    Format: Online
    Series: Array ; DP19479
    Subjects: Large Language Models; Transformer models; Text as data; Unstructured Data
    Scope: 1 Online-Ressource (circa 24 Seiten)
  7. Quality and accountability of Large Language Models (LLMs) in healthcare in low- and middle-income countries (LMIC)
    a simulated patient study using ChatGPT
    Author: Si, Yafei; Yang, Yuji; Wang, Xi; An, Ruopeng; Zu, Jiaqi; Chen, Xi; Fan, Xiaojing; Gong, Sen
    Published: [2024]
    Publisher:  Global Labor Organization (GLO), Essen

    Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find... more

    Access:
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 565
    Inter-library loan:
    No inter-library loan

     

    Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find ChatGPT's performance varied within a single disease, despite a high level of accuracy in both correct diagnosis (74.1%) and medication prescription (84.5%). Additionally, ChatGPT recommended a concerning level of unnecessary or harmful medications (85.2%) even with correct diagnoses. Finally, ChatGPT performed better in managing non-communicable diseases compared to infectious ones. These results highlight the need for cautious AI integration in healthcare systems to ensure quality and safety

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/300730
    Series: GLO discussion paper ; no. 1472
    Subjects: ChatGPT; Large Language Models; Generative AI; Simulated Patient; Healthcare; Quality; Safety; Low- and Middle-Income Countries
    Scope: 1 Online-Ressource (circa 10 Seiten), Illustrationen
  8. Automatic product classification in international trade
    machine learning and large language models
    Author: Marra de Artiñano, Ignacio; Riottini Depetris, Franco; Volpe Martincus, Christian
    Published: July 2023
    Publisher:  Inter-American Development Bank, Integration and Trade Sector, [Washington, DC]

    Accurately classifying products is essential in international trade. Virtually all countries categorize products into tariff lines using the Harmonized System (HS) nomenclature for both statistical and duty collection purposes. In this paper, we... more

    Access:
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 144
    Inter-library loan:
    No inter-library loan

     

    Accurately classifying products is essential in international trade. Virtually all countries categorize products into tariff lines using the Harmonized System (HS) nomenclature for both statistical and duty collection purposes. In this paper, we apply and assess several different algorithms to automatically classify products based on text descriptions. To do so, we use agricultural product descriptions from several public agencies, including customs authorities and the United States Department of Agriculture (USDA). We find that while traditional machine learning (ML) models tend to perform well within the dataset in which they were trained, their precision drops dramatically when implemented outside of it. In contrast, large language models (LLMs) such as GPT 3.5 show a consistently good performance across all datasets, with accuracy rates ranging between 60% and 90% depending on HS aggregation levels. Our analysis highlights the valuable role that artificial intelligence (AI) can play in facilitating product classification at scale and, more generally, in enhancing the categorization of unstructured data.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/299437
    Edition: This version: July 2023
    Series: IDB working paper series ; no IDB-WP-01494
    Subjects: Product Classification; Machine Learning; Large Language Models; Trade
    Scope: 1 Online-Ressource (circa 37 Seiten), Illustrationen
  9. How good are LLMs in risk profiling?
    Author: Hens, Thorsten; Nordlie, Trine
    Published: [2024]
    Publisher:  Swiss Finance Institute, Geneva

    Access:
    Resolving-System (kostenfrei)

    Location:
    Helmut-Schmidt-Universität, Universität der Bundeswehr Hamburg, Universitätsbibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    Keine Rechte
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    Series: Swiss Finance Institute research paper series ; no 24, 30
    Subjects: Large Language Models; ChatGPT; Bard; Risk Profiling
    Scope: 1 Online-Ressource (circa 21 Seiten)
  10. Automated Social Science
    Language Models as Scientist and Subjects
    Author: Manning, Benjamin S.; Zhu, Kehang; Horton, John J.
    Published: April 2024
    Publisher:  National Bureau of Economic Research, Cambridge, Mass

    We present an approach for automatically generating and testing, in silico, social scientific hypotheses. This automation is made possible by recent advances in large language models (LLM), but the key feature of the approach is the use of structural... more

    Access:
    Verlag (lizenzpflichtig)
    Resolving-System (lizenzpflichtig)

    Location:
    Sächsische Landesbibliothek - Staats- und Universitätsbibliothek Dresden
    Inter-library loan:
    No inter-library loan

    Location:
    Universitätsbibliothek Freiburg
    Inter-library loan:
    No inter-library loan

    Location:
    Helmut-Schmidt-Universität, Universität der Bundeswehr Hamburg, Universitätsbibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    Staats- und Universitätsbibliothek Hamburg Carl von Ossietzky
    Inter-library loan:
    No inter-library loan

    Location:
    Technische Informationsbibliothek (TIB) / Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek
    Inter-library loan:
    No inter-library loan

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Inter-library loan:
    No inter-library loan

     

    We present an approach for automatically generating and testing, in silico, social scientific hypotheses. This automation is made possible by recent advances in large language models (LLM), but the key feature of the approach is the use of structural causal models. Structural causal models provide a language to state hypotheses, a blueprint for constructing LLM-based agents, an experimental design, and a plan for data analysis. The fitted structural causal model becomes an object available for prediction or the planning of follow-on experiments. We demonstrate the approach with several scenarios: a negotiation, a bail hearing, a job interview, and an auction. In each case, causal relationships are both proposed and tested by the system, finding evidence for some and not others. We provide evidence that the insights from these simulations of social interactions are not available to the LLM purely through direct elicitation. When given its proposed structural causal model for each scenario, the LLM is good at predicting the signs of estimated effects, but it cannot reliably predict the magnitudes of those estimates. In the auction experiment, the in silico simulation results closely match the predictions of auction theory, but elicited predictions of the clearing prices from the LLM are inaccurate. However, the LLM's predictions are dramatically improved if the model can condition on the fitted structural causal model. In short, the LLM knows more than it can (immediately) tell

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Series: NBER working paper series ; no. w32381
    Subjects: Verhalten; Kausalanalyse; Künstliche Intelligenz; Ökonometrisches Modell; Large Language Models; General; Micro-Based Behavioral Economics
    Scope: 1 Online-Ressource, illustrations (black and white)
    Notes:

    Hardcopy version available to institutional subscribers
  11. How good are LLMs in risk profiling?
    Author: Hens, Thorsten; Nordlie, Trine
    Published: April 2024
    Publisher:  Kyoto University, Kyoto, Japan

    Access:
    Verlag (kostenfrei)
    Verlag (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    VS 766
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Series: KIER discussion paper series ; no. 1103
    Subjects: Large Language Models; ChatGPT; Bard; Risk Profiling
    Scope: 1 Online-Ressource (circa 17 Seiten)
  12. Conducting qualitative interviews with AI
    Author: Chopra, Felix; Haaland, Ingar
    Published: [2023]
    Publisher:  CEBI, Department of Economics, University of Copenhagen, Copenhagen

    Qualitative interviews are one of the fundamental tools of empirical social science research and give individuals the opportunity to explain how they understand and interpret the world, allowing researchers to capture detailed and nuanced insights... more

    Access:
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    DS 814
    Inter-library loan:
    No inter-library loan

     

    Qualitative interviews are one of the fundamental tools of empirical social science research and give individuals the opportunity to explain how they understand and interpret the world, allowing researchers to capture detailed and nuanced insights into complex phenomena. However, qualitative interviews are seldom used in economics and other disciplines inclined toward quantitative data analysis, likely due to concerns about limited scalability, high costs, and low generalizability. In this paper, we introduce an AI-assisted method to conduct semi-structured interviews. This approach retains the depth of traditional qualitative research while enabling large-scale, cost-effective data collection suitable for quantitative analysis. We demonstrate the feasibility of this approach through a large-scale data collection to understand the stock market participation puzzle. Our 395 interviews allow for quantitative analysis that we demonstrate yields richer and more robust conclusions compared to qualitative interviews with traditional sample sizes as well as to survey responses to a single open-ended question. We also demonstrate high interviewee satisfaction with the AI-assisted interviews. In fact, a majority of respondents indicate a strict preference for AI-assisted interviews over human-led interviews. Our novel AI-assisted approach bridges the divide between qualitative and quantitative data analysis and substantially lowers the barriers and costs of conducting qualitative interviews at scale.

     
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Other identifier:
    hdl: 10419/298540
    Edition: This version: September 15, 2023
    Series: CEBI working paper series ; 23, 06
    Subjects: Artificial Intelligence; Interviews; Large Language Models; Qualitative Methods; Stock Market Participation
    Scope: 1 Online-Ressource (circa 73 Seiten), Illustrationen
  13. Recovering overlooked information in categorical variables with LLMs
    an application to labor market mismatch
    Author: Chen, Yi; Fang, Hanming; Zhao, Yi; Zhao, Zibo
    Published: July 23, 2024
    Publisher:  Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, Philadelphia, PA

    Access:
    Verlag (kostenfrei)
    Verlag (kostenfrei)

    Location:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signature:
    Keine Rechte
    Inter-library loan:
    No inter-library loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Union catalogues
    Language: English
    Media type: Book
    Format: Online
    Series: PIER working paper ; 24, 017
    Subjects: Large Language Models; Categorical Variables; Labor Market Mismatch
    Scope: 1 Online-Ressource (circa 48 Seiten), Illustrationen
  14. Large language models in economics
    Author: Ash, Elliott; Hansen, Stephen; Muvdi, Yabra
    Published: 13 September 2024
    Publisher:  Centre for Economic Policy Research, London

    Access:
    Verlag (Deutschlandweit zugänglich)
    Verlag (Deutschlandweit zugänglich)

    Location:
    Staatsbibliothek zu Berlin - Preußischer Kulturbesitz, Haus Unter den Linden
    Inter-library loan:
    Unlimited inter-library loan, copies and loan

    Location:
    Universität Potsdam, Universitätsbibliothek
    Inter-library loan:
    Unlimited inter-library loan, copies and loan
    Export to reference management software   RIS file
      BibTeX file
    Source: Staatsbibliothek zu Berlin
    Language: English
    Media type: Book
    Format: Online
    Series: Array ; DP19479
    Subjects: Large Language Models; Transformer models; Text as data; Unstructured Data
    Scope: 1 Online-Ressource (circa 24 Seiten)