A standard assumption in research on pronoun use is that production and interpretation are guided by the same set of contextual factors. Kehler et al. (2008) and Kehler & Rohde (2013) have argued instead for a Bayesian model, according to which pronoun production is insensitive to a class of semantic and pragmatic biases that have been shown to influence interpretation. We evaluate the model using a passage completion study that employs a contextual manipulation to which traditional analyses are insensitive, specifically by varying whether a relative clause that modifies the direct object in the context sentence invites the inference of a cause. The results support the claim that pronoun interpretation biases, but not production biases, are sensitive to this pragmatic enrichment, revealing the asymmetry predicted by the Bayesian analysis. A correlation analysis further establishes that the model provides better estimates of measured pronoun interpretation biases than two competing models.