Search Results for author:
Found 3 papers, 1 papers with code
Trusted Source Alignment in Large Language Models
Large language models (LLMs) are trained on web-scale corpora that inevitably include contradictory factual information from sources of varying reliability.
Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset.
Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models
Using a template-based data collection pipeline, we collect 396K sentence completions made by GPT-2 and find: (i) The machine-predicted jobs are less diverse and more stereotypical for women than for men, especially for intersections; (ii) Intersectional interactions are highly relevant for occupational associations, which we quantify by fitting 262 logistic models; (iii) For most occupations, GPT-2 reflects the skewed gender and ethnicity distribution found in US Labor Bureau data, and even pulls the societally-skewed distribution towards gender parity in cases where its predictions deviate from real labor market observations.
