https://statmodeling.stat.columbia.edu/2024/05/21/what-to-make-of-implicit-biases-in-llm-output
What to make of implicit biases in LLM output?
Jessica Hullman
5/21/24 12:27 PM
“…when you prompt a number of large language models to do IAT-inspired tasks and make associated decisions, they exhibit implicit biases…. Of course we shouldn’t expect the model development process to eliminate all appearances of correlations between concepts that we don’t like in model output. Consequently it shouldn’t come as a surprise that we can construct examples of prompts and associated decisions that exhibit bias.”