Are Emergent Abilities of Large Language Models a Mirage?
Schaeffer et al., 2023, Are Emergent Abilities of Large Language Models a Mirage? (Advances in Neural Information Processing Systems 36 (NeurIPS 2023))
Subscriber deck — free during early access
1 cards in “6 Limitations” · whole deck
6 Limitations
- Do Schaeffer et al. claim that language models cannot have emergent abilities?No: they argue only that some previously claimed emergent abilities appear to be mirages created by researcher choices. Some private models couldn’t be analyzed, and whether human judgments of quality are themselves thresholded remains open.
- Schaeffer et al., 2023, Are Emergent Abilities of Large Language Models a Mirage? (Advances in Neural Information Processing Systems 36 (NeurIPS 2023)), §6
Source
- Rylan Schaeffer, Brando Miranda and Sanmi Koyejo. 2023. Are Emergent Abilities of Large Language Models a Mirage?. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023). https://papers.nips.cc/paper_files/paper/2023/hash/adc98a266f45005c403b8311ca7e8bd7-Abstract-Conference.html