Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhagat, Kirti, Vasisht, Kinshuk, Pruthi, Danish
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916618743840768
author Bhagat, Kirti
Vasisht, Kinshuk
Pruthi, Danish
author_facet Bhagat, Kirti
Vasisht, Kinshuk
Pruthi, Danish
contents While a large body of work inspects language models for biases concerning gender, race, occupation and religion, biases of geographical nature are relatively less explored. Some recent studies benchmark the degree to which large language models encode geospatial knowledge. However, the impact of the encoded geographical knowledge (or lack thereof) on real-world applications has not been documented. In this work, we examine large language models for two common scenarios that require geographical knowledge: (a) travel recommendations and (b) geo-anchored story generation. Specifically, we study five popular language models, and across about $100$K travel requests, and $200$K story generations, we observe that travel recommendations corresponding to poorer countries are less unique with fewer location references, and stories from these regions more often convey emotions of hardship and sadness compared to those from wealthier nations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07320
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
Bhagat, Kirti
Vasisht, Kinshuk
Pruthi, Danish
Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
While a large body of work inspects language models for biases concerning gender, race, occupation and religion, biases of geographical nature are relatively less explored. Some recent studies benchmark the degree to which large language models encode geospatial knowledge. However, the impact of the encoded geographical knowledge (or lack thereof) on real-world applications has not been documented. In this work, we examine large language models for two common scenarios that require geographical knowledge: (a) travel recommendations and (b) geo-anchored story generation. Specifically, we study five popular language models, and across about $100$K travel requests, and $200$K story generations, we observe that travel recommendations corresponding to poorer countries are less unique with fewer location references, and stories from these regions more often convey emotions of hardship and sadness compared to those from wealthier nations.
title Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
topic Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2411.07320