Although the success of the Papanicolaou test as a screening tool of cervical cancer is evident, there still exists $2{sim}5%$ of discrepancy rate by both human and machine. To improve the qualilty of cervico-vaginal cytology, the authors compared cervicovaginal smear with cervical biopsy diagnoses, and analysed the causes of discrepancies. Among 30,922 cervicovaginal smears from June 1996 to April 1997 at our hospital, there were 271 cases of cervicovaginal smear with subsequent cervical punch or LEEP cone biopsies within several months. The biopsies and smears from a total of 98 discordant cases were reviewed. The discrepancy was attributed to sampling errors in 43 cases(43.9%), and to cytologic diagnosis in 49 cases(50.0%). Among these, 43 cases were interpretative errors(categories A;19, B;16 and C;8) whereas six cases were screening errors(categories B:2 and C:4). Among cervical biopsy cases, errors were present in four. As for 10% random rescreening, cytotechnologists reviewed 3,196 of 30,922 smears during the same period, There were 43 cases of screening error(categories A;27, B;16). Cytologic/histologic correlation was superior to 10% random rescreening of negative cases. The most effective method for quality improvement in cervicovaginal cytology was to implement both quality control(rescreening) and qualify assurance(cytologic/histologic correlation) programs.