The benefits, risks and bounds of personalizing the alignment of large language models to individuals
Large language models (LLMs) undergo ‘alignment’ so that they better reflect human values or preferences, and are safer or more useful. However, alignment is intrinsically difficult because the hundreds of millions of people who now interact with LLMs have different preferences for language and conv...
Autors principals: | Kirk, HR, Vidgen, B, Röttger, P, Hale, SA |
---|---|
Format: | Journal article |
Idioma: | English |
Publicat: |
Springer Nature
2024
|
Ítems similars
-
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
per: Kirk, HR, et al.
Publicat: (2022) -
Is more data better? re-thinking the importance of efficiency in abusive language detection with transformers-based active learning
per: Kirk, HR, et al.
Publicat: (2022) -
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
per: Kirk, H, et al.
Publicat: (2021) -
Exploring large language models for ontology alignment
per: He, Y, et al.
Publicat: (2023) -
Survey on large language models alignment research
per: LIU Kunlin, et al.
Publicat: (2024-06-01)