|
on Artificial Intelligence |
| By: | Occhipinti, Jo-An; Hynes, William; Prodan, Ante; Eyre, Harris; Green, Roy; Burrow, Sharan; Tanner, Marcel; Buchanan, John; Ujdur, Goran; Destrebecq, Frederic; Song, Christine; Carnevale, Steven; Hickie, Ian B.; Heffernan, Mark |
| Abstract: | Work is fundamental to societal prosperity and mental health, providing financial security, a sense of identity and purpose, and social integration. Job insecurity, underemployment and unemployment are well-documented risk factors for mental health issues and suicide. The emergence of generative artificial intelligence (AI) has catalysed debate on job displacement and its corollary impacts on individual and social wellbeing. Some argue that many new jobs and industries will emerge to offset the displacement, while others foresee a widespread decoupling of economic productivity from human input threatening jobs on an unprecedented scale. This study explores the conditions under which both may be true and examines the potential for a self-reinforcing cycle of recessionary pressures that would necessitate sustained government intervention to maintain job security and economic stability. A system dynamics model was developed to undertake ex ante analysis of the effect of AI-capital deepening on labour underutilisation and demand in the economy using Australian data as a case study. Results indicate that even a moderate increase in the AI-capital-to-labour ratio could increase labour underutilisation to double its current level, decrease per capita disposable income by 26% (95% interval, 20.6–31.8%), and decrease the consumption index by 21% (95% interval, 13.6–28.3%) by mid-2050. To prevent a reduction in per capita disposable income due to the estimated increase in underutilization, at least a 10.8-fold increase in the new job creation rate would be necessary. Results demonstrate the feasibility of an AI-capital-to-labour ratio threshold beyond which even high rates of new job creation cannot prevent declines in consumption. The precise threshold will vary across economies, emphasizing the urgent need for empirical research tailored to specific contexts. This study underscores the need for cross-sectoral government measures to ensure a smooth transition to an AI-dominated economy to safeguard the Mental Wealth of nations. |
| Keywords: | artificial intelligence; economic policy; wellbeing; wystem dynamics; recession |
| JEL: | N0 R14 J01 |
| Date: | 2025–07–18 |
| URL: | https://d.repec.org/n?u=RePEc:ehl:lserod:128885 |
| By: | Darija Barak; Miguel Costa-Gomes |
| Abstract: | As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled monetarily-incentivised laboratory experiment looking at differences in human behaviour in a multi-player p-beauty contest against other humans and LLMs. We use a within-subject design in order to compare behaviour at the individual level. We show that, in this environment, human subjects choose significantly lower numbers when playing against LLMs than humans, which is mainly driven by the increased prevalence of `zero' Nash-equilibrium choices. This shift is mainly driven by subjects with high strategic reasoning ability. Subjects who play the zero Nash-equilibrium choice motivate their strategy by appealing to perceived LLM's reasoning ability and, unexpectedly, propensity towards cooperation. Our findings provide foundational insights into the multi-player human-LLM interaction in simultaneous choice games, uncover heterogeneities in both subjects' behaviour and beliefs about LLM's play when playing against them, and suggest important implications for mechanism design in mixed human-LLM systems. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.11011 |
| By: | Prasanna Parasurama; Panos Ipeirotis |
| Abstract: | Algorithmic tools are increasingly used in hiring to improve fairness and diversity, often by enforcing constraints such as gender-balanced candidate shortlists. However, we show theoretically and empirically that enforcing equal representation at the shortlist stage does not necessarily translate into more diverse final hires, even when there is no gender bias in the hiring stage. We identify a crucial factor influencing this outcome: the correlation between the algorithm's screening criteria and the human hiring manager's evaluation criteria -- higher correlation leads to lower diversity in final hires. Using a large-scale empirical analysis of nearly 800, 000 job applications across multiple technology firms, we find that enforcing equal shortlists yields limited improvements in hire diversity when the algorithmic screening closely mirrors the hiring manager's preferences. We propose a complementary algorithmic approach designed explicitly to diversify shortlists by selecting candidates likely to be overlooked by managers, yet still competitive according to their evaluation criteria. Empirical simulations show that this approach significantly enhances gender diversity in final hires without substantially compromising hire quality. These findings highlight the importance of algorithmic design choices in achieving organizational diversity goals and provide actionable guidance for practitioners implementing fairness-oriented hiring algorithms. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.14388 |
| By: | Capistrano, Daniel (University College Dublin); Creighton, Mathew (University College Dublin); Fernández-Reino, Mariña |
| Abstract: | In this study, we assessed if Large Language Models provided biased answers when prompted to assist with the evaluation of requests made by individuals with different ethnic backgrounds and gender. We emulated an experimental procedure traditionally used in correspondence studies to test discrimination in social settings. The preference given as recommendation from the language models were compared across groups revealing a significant bias against names associated with ethnic minorities, particularly in the housing domain. However, the magnitude of this ethnic bias as well as differences by gender depended on the context mentioned in the prompt to the model. Finally, directing the model to take into consideration regulatory provisions on Artificial Intelligence or potential gender and ethnic discrimination does not seem to mitigate the observed bias between groups. |
| Date: | 2025–07–06 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:9zusq_v1 |
| By: | Dessart François (European Commission - JRC); Fernandez Macias Enrique (European Commission - JRC); Gomez Gutierrez Emilia (European Commission - JRC) |
| Abstract: | The Joint Research Centre has developed a methodology to assess the relative impact of AI on occupations. It is based on a mapping between the amount of research in AI and occupations, linking them through cognitive abilities and work tasks.The methodology was used to calculate an AI exposure score for 100+ occupations. AI has the largest impact on occupations such as engineers, administration professionals (including policymakers), and teachers. In contrast, cleaners and construction labourers are much less impacted by AI. With the fast advancement of AI, this score can be updated to anticipate the likely impact of emerging AI technologies on occupations. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:ipt:iptwpa:jrc142580 |
| By: | Junzhe Jiang; Chang Yang; Aixin Cui; Sihan Jin; Ruiyu Wang; Bo Li; Xiao Huang; Dongning Sun; Xinrun Wang |
| Abstract: | Financial tasks are pivotal to global economic stability; however, their execution faces challenges including labor intensive processes, low error tolerance, data fragmentation, and tool limitations. Although large language models (LLMs) have succeeded in various natural language processing tasks and have shown potential in automating workflows through reasoning and contextual understanding, current benchmarks for evaluating LLMs in finance lack sufficient domain-specific data, have simplistic task design, and incomplete evaluation frameworks. To address these gaps, this article presents FinMaster, a comprehensive financial benchmark designed to systematically assess the capabilities of LLM in financial literacy, accounting, auditing, and consulting. Specifically, FinMaster comprises three main modules: i) FinSim, which builds simulators that generate synthetic, privacy-compliant financial data for companies to replicate market dynamics; ii) FinSuite, which provides tasks in core financial domains, spanning 183 tasks of various types and difficulty levels; and iii) FinEval, which develops a unified interface for evaluation. Extensive experiments over state-of-the-art LLMs reveal critical capability gaps in financial reasoning, with accuracy dropping from over 90% on basic tasks to merely 40% on complex scenarios requiring multi-step reasoning. This degradation exhibits the propagation of computational errors, where single-metric calculations initially demonstrating 58% accuracy decreased to 37% in multimetric scenarios. To the best of our knowledge, FinMaster is the first benchmark that covers full-pipeline financial workflows with challenging tasks. We hope that FinMaster can bridge the gap between research and industry practitioners, driving the adoption of LLMs in real-world financial practices to enhance efficiency and accuracy. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.13533 |
| By: | Gianluca De Nard; Damjan Kostovic |
| Abstract: | The paper introduces a new type of shrinkage estimation that is not based on asymptotic optimality but uses artificial intelligence (AI) techniques to shrink the sample eigenvalues. The proposed AI Shrinkage estimator applies to both linear and nonlinear shrinkage, demonstrating improved performance compared to the classic shrinkage estimators. Our results demonstrate that reinforcement learning solutions identify a downward bias in classic shrinkage intensity estimates derived under the i.i.d. assumption and automatically correct for it in response to prevailing market conditions. Additionally, our data-driven approach enables more efficient implementation of risk-optimized portfolios and is well-suited for real-world investment applications including various optimization constraints. |
| Keywords: | Covariance matrix estimation, linear and nonlinear shrinkage, portfolio management reinforcement learning, risk optimization |
| JEL: | C13 C58 G11 |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:zur:econwp:470 |