Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries
We study how multilingual sentence representations capture European countries and occupations and how this differs across European languages. We prompt the models with templated sentences that we machine-translate into 12 European languages and analyze the most prominent dimensions in the embeddings.Our analysis reveals that the most prominent feature in the embedding is the geopolitical distinction between Eastern and Western Europe and the country's economic strength in terms of GDP. When prompted specifically for job prestige, the embedding space clearly distinguishes high and low-prestige jobs. The occupational dimension is uncorrelated with the most dominant country dimensions in three out of four studied models. The exception is a small distilled model that exhibits a connection between occupational prestige and country of origin, which is a potential source of nationality-based discrimination. Our findings are consistent across languages.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSentence EmbeddingsSimilar Papers 제목 키워드 기반
Presence of Women in Economics Academia: Evidence from India
This paper documents the representation of women in Economics academia in India by analyzing the share of women in faculty positions, and their participation in a prestigious conference held annually. Data from the elite…
DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models
We introduce DebateBench, a novel dataset consisting of an extensive collection of transcripts and metadata from some of the world's most prestigious competitive debates. The dataset consists of British Parliamentary deb…
In-Context LearningAI Governance in Higher Education: Case Studies of Guidance at Big Ten Universities
Generative AI has drawn significant attention from stakeholders in higher education. As it introduces new opportunities for personalized learning and tutoring support, it simultaneously poses challenges to academic integ…
Causal Inference under Outcome-Based Sampling with Monotonicity Assumptions
We study causal inference under case-control and case-population sampling. Specifically, we focus on the binary-outcome and binary-treatment case, where the parameters of interest are causal relative and attributable ris…
Causal InferenceCreative Problem Solving in Large Language and Vision Models -- What Would it Take?
We advocate for a strong integration of Computational Creativity (CC) with research in large language and vision models (LLVMs) to address a key limitation of these models, i.e., creative problem solving. We present prel…