Search Results for author:
Found 5 papers, 3 papers with code
Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory
Our findings lead us to call for a re-evaluation of how gendered harms in language models are defined and addressed.
Clinical knowledge in LLMs does not translate to human interactions
Tested alone, LLMs complete the scenarios accurately, correctly identifying conditions in 94. 9% of cases and disposition in 56. 3% on average.
Characterizing and modeling harms from interactions with design patterns in AI interfaces
The proliferation of applications using artificial intelligence (AI) systems has led to a growing number of users interacting with these systems through sophisticated interfaces.
Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports
Here, we partner with a Brazilian human rights organization to conduct a systematic evaluation of language models to assist with monitoring real-world firearm events from social media data.
A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data
The best method evaluated, a differentially private SDG mechanism, can provide both protection against inference attacks and reasonable utility, but only in very specific settings.
