basically just [[large language model]]s at this point (2023-06-12),
in [[deep learning]] at least (in terms of [[generative model]]s)
(mostly [[transformer architecture]]s, though maybe [[state space model]] are on their way?)
it seems like actual models based on [[form]]al language theory or [[linguistic]]s are pretty rare nowadays...
see [[relational representation|neurosymbolic]]
some questions:
- How do [[natural language processing|language model]]s [[represent|represent]] language?
- How do [[Homo sapiens|human]]s represent language?
- How *should* language models represent language?
- [[multilingualism in language models]] (including questions of [[linguistic relativity]])
- [[language model language acquisition]] and [[interpretable training method]]s for language
# autogenerated index
- [[n-gram]]
- [[autoregressive]]
- [[decoder-only transformer]]
- [[ChatGPT]]
- [[2020BrownEtAlLanguageModelsAre]]
- [[2023KorbakEtAlPretrainingLanguageModels]]
- [[2022MengEtAlLocatingEditingFactual]]
- [[2023OpenAIGPT4TechnicalReport]]
- [[2018RadfordEtAlImprovingLanguageUnderstanding]]
- [[2019RadfordEtAlLanguageModelsAre]]
- [[2022YuEtAlScalingAutoregressiveModels]]
- [[text dataset]]
- [[Stanford human preferences dataset]]
- [[2020CohanEtAlSPECTERDocumentlevelRepresentation]]
- [[steering language models]]
- [[context-free text representations]]
- [[2013MikolovEtAlDistributedRepresentationsWords]]
- [[2013MikolovEtAlEfficientEstimationWord]]
- [[2014PenningtonEtAlGloVeGlobalVectors]]
- [[large language model]]
- [[large language model evaluation]]
- [[2023ChiaEtAlINSTRUCTEVALHolisticEvaluation]]
- [[2023GanguliEtAlCapacityMoralSelfcorrection]]
- [[2020SaundersEtAlEvaluatingArgumentsOne]]
- [[2023ShevlaneEtAlModelEvaluationExtreme]]
- [[compute-optimal training]]
- [[the llama craze]]
- [[2023ChiangEtAlVicunaOpensourceChatbot]]
- [[2023TouvronEtAlLlama2Open]]
- [[language model dataset generation]]
- [[2023PenedoEtAlRefinedWebDatasetFalcon]]
- [[prompt engineering]]
- [[2023CohenEtAlCrawlingInternalKnowledgebase]]
- [[2023WangEtAlVoyagerOpenendedEmbodied]]
- [[2023ZhuEtAlGhostMinecraftGenerally]]
- [[BlenderBot]]
- [[ChatGPT]]
- [[2023AkashOvertonWindowWidens]]
- [[2020BrownEtAlLanguageModelsAre]]
- [[2022ChowdheryEtAlPaLMScalingLanguage]]
- [[2023GanguliEtAlCapacityMoralSelfcorrection]]
- [[2023GunasekarEtAlTextbooksAreAll]]
- [[noauthor_vllm-projectvllm_2023]]
- [[2022SrivastavaEtAlImitationGameQuantifying]]
- [[2022AnonymousLargeLanguageModels]]
- [[2019LiuEtAlRoBERTaRobustlyOptimized]]
- [[2022OlssonEtAlIncontextLearningInduction]]
- [[2022VermaEtAlCHAIChatbotAI]]
^114
# sources
https://plato.stanford.edu/entries/computational-linguistics/
https://direct.mit.edu/coli/issue/browse-by-year