Semantic Distance
A quantitative metric for measuring associative creativity, defined as the degree of deviation between a generated description and a reference semantic space (such as a word-vector space or concept ontology), used to assess originality.
Timeline (last 90 days)
Compared with multimodal large models, the associative descriptions produced by humans have greater semantic distance, higher entropy, and more novel expressions.
Semantic distance is one of the quantitative metrics for measuring associative creativity, defined as the degree of deviation between generated descriptions and a reference semantic space; entropy characterizes the distributional disorder of a set of descriptions across semantic categories.
Combining semantic distance and entropy can distinguish 'random nonsense' from 'meaningful originality': the former has large semantic distance but low effectiveness, while the latter achieves high distance and high entropy while maintaining comprehensibility.
All Facts (3)
Compared with multimodal large models, the associative descriptions produced by humans have greater semantic distance, higher entropy, and more novel expressions.
50%UnverifiedSemantic distance is one of the quantitative metrics for measuring associative creativity, defined as the degree of deviation between generated descriptions and a reference semantic space; entropy characterizes the distributional disorder of a set of descriptions across semantic categories.
50%UnverifiedCombining semantic distance and entropy can distinguish 'random nonsense' from 'meaningful originality': the former has large semantic distance but low effectiveness, while the latter achieves high distance and high entropy while maintaining comprehensibility.
50%