Semantic Similarity is a task carried out in NLP and Legal NLP. It involves determining the similarity between texts. Given two passages of text, a model can determine how similar or dissimilar they are from one another. In the context of Legal NLP, the two passages of text could be two clauses or two documents. Semantic similarity is useful in Legal NLP in detecting deviations in drafting or automatically surfacing risky positions during drafting and review.