Verbs often participate in more than 1 syntactic structure, but individual verbs can be biased in terms of whether they are used more often with 1 structure or the other. For instance, in a sentence such as “Bop the bunny with the flower,” the phrase “with the flower” is more likely to indicate an instrument with which to “bop,” rather than which “bunny” to bop. Conversely, in a sentence such as “Choose the cow with the flower,” the phrase “with the flower” is more likely to indicate which “cow” to choose. An open question is where these biases come from and whether they continue to be shaped in adulthood in a way that has lasting consequences for real-time processing of language. In Experiment 1 we replicated previous findings that these language-wide biases guide online syntactic processing in a computer-based visual-world paradigm. In Experiment 2, we tested the malleability of these biases by exposing adults to initially unbiased verbs situated in unambiguous contexts that led to either instrument or modifier interpretations. During test, participants interpreted sentences containing either modifier- or instrument-trained verbs in ambiguous contexts. Eye-movement and action data show that participants’ considerations of the candidate interpretations of the ambiguous with-phrases were guided by the newly learned verb biases. These results suggest that co-occurrence information about specific verbs and syntactic structures embedded in language experiences plays a role in forming, and continuously shaping, the verb biases that constitute a part of the broader representation of the language.