Searcharxiv⌕ Search

arXiv subjects

Arif Akgul

Publications and source records attributed to Arif Akgul.

2 recordsLinked to original sources

Do Machines Learn Deviance From Their Peers? A Randomized Test of Differential Association With AI Agents

Differential association theory and its extension, social learning theory, hold that rule-breaking, and the definitions that make it acceptable, are learned through interaction with others. Because people choose their friends, this claim has been hard to test. We addressed this selection problem with AI agents, which learn only through communication and can be assigned to peers at random. In a preregistered experiment, 420 teams of three agents (1,260 agents; seven AI models) worked on coding tasks that could not be solved honestly. A scripted teammate said that it had cheated (deviant peer), that it had reported the problem honestly (honest peer), or said nothing (silent peer). Half of the teams were told that an auditor read their chat. Compared with a silent peer, a deviant peer increased cheating (66.2% vs. 62.9%; OR = 1.96) and an honest peer reduced it (55.7%; OR = 0.35). Among agents that cheated, a deviant peer increased claims that cheating was normal (13.7% vs. 3.4%), often as the team's norm. Monitoring did not suppress prohibited discussion; it doubled it. Peers mattered only for models that had not yet decided. AI agents offer a new way to test criminological learning theories without selection effects.

cs.AI↗

Not as Simple as It Looked: Are We Concluding for Biased Arrest Practices?

This study examines racial disparities in violent arrest outcomes, challenging conventional methods through a nuanced analysis of Cincinnati Police Department data. Acknowledging the intricate nature of racial disparity, the study categorizes explanations into types of place, types of person, and a combination of both, emphasizing the impact of neighborhood characteristics on crime distribution and police deployment. By introducing alternative scenarios, such as spuriousness, directed policing, and the geo-concentration of racial groups, the study underscores the complexity of racial disparity calculations. Employing a case study approach, the analysis of violent arrest outcomes reveals approximately 40 percent of the observed variation attributed to neighborhood-level characteristics, with concentrated disadvantage neutralizing the influence of race on arrest rates. Contrary to expectations, the study challenges the notion of unintentional racism, suggesting that neighborhood factors play a more significant role than the racial composition in explaining arrests. Policymakers are urged to focus on comprehensive community development initiatives addressing socioeconomic inequalities and support the development of robust racial disparity indices. The study calls for nuanced explorations of unintentional racism and future research addressing potential limitations, aiming to enhance understanding of the complexities surrounding racial disparities in arrests.

cs.CY↗