Ai suggestions homogenize writing toward western styles and diminish cultural nuances
Large language models (LLMs) are being increasingly integrated into everyday products
and services, such as coding tools and writing assistants. As these embedded AI …
and services, such as coding tools and writing assistants. As these embedded AI …
Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyone
This paper presents a vision for creating AI systems that are inclusive at every stage of
development, from data collection to model design and evaluation. We address key …
development, from data collection to model design and evaluation. We address key …
Evaluating Large Language Models with fmeval
P Schwöbel, L Franceschi, MB Zafar, K Vasist… - arXiv preprint arXiv …, 2024 - arxiv.org
fmeval is an open source library to evaluate large language models (LLMs) in a range of
tasks. It helps practitioners evaluate their model for task performance and along multiple …
tasks. It helps practitioners evaluate their model for task performance and along multiple …
Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
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 …
occupation and religion, biases of geographical nature are relatively less explored. Some …
Saxony-Anhalt is the Worst: Bias Towards German Federal States in Large Language Models
A Kruspe, M Stillman - German Conference on Artificial Intelligence …, 2024 - Springer
Recent research demonstrates geographic biases in various Large Language Models that
reflects common human biases, which are presumably present in the training data. We …
reflects common human biases, which are presumably present in the training data. We …
Large language models as recommender systems: A study of popularity bias
JM Lichtenberg, A Buchholz, P Schwöbel - arXiv preprint arXiv …, 2024 - arxiv.org
The issue of popularity bias--where popular items are disproportionately recommended,
overshadowing less popular but potentially relevant items--remains a significant challenge …
overshadowing less popular but potentially relevant items--remains a significant challenge …