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...
Main Authors: | Kirk, HR, Vidgen, B, Röttger, P, Hale, SA |
---|---|
Format: | Journal article |
Sprog: | English |
Udgivet: |
Springer Nature
2024
|
Lignende værker
-
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
af: Kirk, HR, et al.
Udgivet: (2022) -
Is more data better? re-thinking the importance of efficiency in abusive language detection with transformers-based active learning
af: Kirk, HR, et al.
Udgivet: (2022) -
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
af: Kirk, H, et al.
Udgivet: (2021) -
Exploring large language models for ontology alignment
af: He, Y, et al.
Udgivet: (2023) -
Survey on large language models alignment research
af: LIU Kunlin, et al.
Udgivet: (2024-06-01)