Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don’t mimic the full human distribution

Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don’t mimic the full human distribution Hayley Ross author Kathryn Davidson author Najoung Kim author 2024-11 text Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP Dieuwke Hupkes editor Verna Dankers editor Khuyagbaatar Batsuren editor Amirhossein Kazemnejad editor Christos Christodoulopoulos editor Mario Giulianelli editor Ryan Cotterell editor Association for Computational Linguistics Miami, Florida, USA conference publication ross-etal-2024-artificial 10.18653/v1/2024.genbench-1.9 https://aclanthology.org/2024.genbench-1.9/ 2024-11 131 153