Secondary Bias
The post-retrieval layer of selection: how an AI model treats, weights, and is swayed by content once it has been retrieved. Unlike primary bias, it is addressable now.
Secondary bias is the post-retrieval layer of how an AI model decides what to use. Where primary bias is what the model already believes before it searches, secondary bias is everything about how your content is formatted, structured, presented, and weighted once it has been retrieved.
It is the addressable layer. Primary bias is slow to move because it lives in the training data; secondary bias can be influenced now, at the margin, through how a page is written and shown. Grounding bias is a form of secondary bias. See also our article on Primary Bias.