Wepresent a new method for information retrieval using hidden Markov models (HMMs). Wedevelop a general framework for incorporating multiple word generation mechanisms within the same model. We then demon-strate that an extremely simple realization of this model substantially outperforms standard tf :idf ranking on both the TREC-6 and TREC-7 ad hoc retrieval tasks. We go on to present a novel method for performing blind feedback in the HMM framework, a more com-plex HMM that models bigram production, and several other algorithmic renements. Together, these meth-ods form a state-of-the-art retrieval system that ranked among the best on the TREC-7 ad hoc retrieval task.