3 papers
cs.CV2024
Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
Pablo Rivas, Gisela Bichler, Tomas Cerny +2
Unbiased representation learning is still an object of study under specific applications and contexts. Novel architectures are usually crafted to resolve particular problems using…
cs.CL2024
Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach
Ernesto Quevedo, Jorge Yero, Rachel Koerner +2
Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring…
cs.LG2024
On the Challenges of Creating Datasets for Analyzing Commercial Sex Advertisements to Assess Human Trafficking Risk and Organized Activity
Pablo Rivas, Tomas Cerny, Alejandro Rodriguez Perez +4
Our study addresses the challenges of building datasets to understand the risks associated with organized activities and human trafficking through commercial sex advertisements. Th…