How User Language Affects Conflict Fatality Estimates in ChatGPT
OpenAI's ChatGPT language model has gained popularity as a powerful tool for complex problem-solving and information retrieval. However, concerns arise about the reproduction of biases present in the language-specific training data. In this study, we address this issue in the context of the Israeli-Palestinian and Turkish-Kurdish conflicts. Using GPT-3.5, we employed an automated query procedure to inquire about casualties in specific airstrikes, in both Hebrew and Arabic for the former conflict and Turkish and Kurdish for the latter. Our analysis reveals that GPT-3.5 provides 27$\pm$11 percent lower fatality estimates when queried in the language of the attacker than in the language of the targeted group. Evasive answers denying the existence of such attacks further increase the discrepancy, creating a novel bias mechanism not present in regular search engines. This language bias has the potential to amplify existing media biases and contribute to information bubbles, ultimately reinforcing conflicts.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalLanguage ModelingLanguage ModellingRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Analyzing Textual Data for Fatality Classification in Afghanistan's Armed Conflicts: A BERT Approach
Afghanistan has witnessed many armed conflicts throughout history, especially in the past 20 years; these events have had a significant impact on human lives, including military and civilians, with potential fatalities. …
Humanitariantext-classificationText ClassificationDetectability of the novel coronavirus (SARS-CoV-2) infection and rates of mortality from the novel coronavirus infection in different regions of the Russian Federation
Relevance: Laboratory diagnosis of the novel coronavirus (SARS-CoV-2) infection combined with quarantine for contacts of infected individuals affects the spread of SARS-CoV-2 infection and levels of related mortality. Pr…
Using excess deaths and testing statistics to improve estimates of COVID-19 mortalities
Factors such as non-uniform definitions of mortality, uncertainty in disease prevalence, and biased sampling complicate the quantification of fatality during an epidemic. Regardless of the employed fatality measure, the …
Cross-Country Age Disparities in COVID-19 Cases with Hospitalization, ICU Usage, and Morbidity
In this paper, we examine cross-country differences, in terms of the age distribution of symptomatic cases, hospitalizations, intensive care unit (ICU) cases, and fatalities due to the novel COVID-19. By calculating cond…
AttributeEstimating effective infection fatality rates during the course of the COVID-19 pandemic in Germany
The infection fatality rate (IFR) of the Coronavirus Disease 2019 (COVID-19) is one of the most discussed figures in the context of this pandemic. Using German COVID-19 surveillance data and age-group specific IFR estima…