The Capacity for Moral Self-Correction in Large Language Models.
Deep GanguliAmanda AskellNicholas SchieferThomas I. LiaoKamile LukosiuteAnna ChenAnna GoldieAzalia MirhoseiniCatherine OlssonDanny HernandezDawn DrainDustin LiEli Tran-JohnsonEthan PerezJackson KernionJamie KerrJared MuellerJoshua LandauKamal NdousseKarina NguyenLiane LovittMichael SellittoNelson ElhageNoemí MercadoNova DasSarmaOliver RauschRobert LasenbyRobin LarsonSam RingerSandipan KunduSaurav KadavathScott JohnstonShauna KravecSheer El ShowkTamera LanhamTimothy Telleen-LawtonTom HenighanTristan HumeYuntao BaiZac Hatfield-DoddsBen MannDario AmodeiNicholas JosephSam McCandlishTom BrownChristopher OlahJack ClarkSamuel R. BowmanJared KaplanPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- speech recognition
- probabilistic model
- language modelling
- n gram
- document retrieval
- retrieval model
- information retrieval
- test collection
- query expansion
- smoothing methods
- ad hoc information retrieval
- statistical language models
- vector space model
- context sensitive
- query terms
- relevance model
- translation model
- document length
- document ranking