Levenshtein distance is an excellent metric to measure the difference between two string data sets, but is Levenshtein a good measure to detect plagiarism between content produced by ChatGPT & a referred source? If not, then what distance measure is more suitable? Cosine?
Cosine should be good I think, ROUGE, BLEU scores could also be used I think.
Thank you. I would read up on this. Very helpful.