We solve the problem of record linkage between databases where record ﬁelds are mixed and permuted in diﬀerent ways. The solution method uses a conditional random ﬁelds model to ﬁnd matching terms in record pairs and uses matching terms in the duplicate detection process. Although records with permuted ﬁelds may have partly reordered terms, our method can still utilize local orders of terms for ﬁnding matching terms. We carried out experiments on several wellknown data sets in record linkage research, and our method showed its advantages on most of the data sets. We also did experiments on a synthetic data set, in which records combined ﬁelds in random order, and veriﬁed that it could handle even this data set.