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