Objective The Thought-Action Fusion Scale (TAFS) is a self-reported instrument used to measure a cognitive bias, namely, thought-action fusion (TAF), in which intrusive thoughts have moral and actual consequences. The aim of this study is to investigate the reliabili-ty and validity of the Korean version of the 19-item TAFS (K-TAFS) in Korean samples. Methods In this study, 628 university students and 93 patients with obsessive-compulsive disorder (OCD) completed the K-TAFS and several other psychological scales. Descriptive analyses, correlations, group comparisons, and exploratory and confirmatory factor anal-yses were performed. Results The results of the exploratory and confirmatory factor analyses indicated a two-factor structure with TAF-Morality and TAF-Likelihood that best fits the data in the university sample. The reliability analyses showed that TAFS and its factors had excellent internal consistencies. Regarding the concurrent validity, positive correlations were observed between TAF-Likelihood and cognitive fusion, while the TAFS scores did not show any consistent correlations with other symptoms such as depression and anxiety. Compared to the university students, the OCD patients showed higher TAFS scores and their obsessive-compulsive symptoms were significantly associat-ed with both TAF-Morality and TAF-Likelihood. Conclusion Overall, the findings of this study support the reliability and validity of the K-TAFS. Psychiatry Investig 2021;18(4):348-356