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...
Những tác giả chính: | Kirk, HR, Vidgen, B, Röttger, P, Hale, SA |
---|---|
Định dạng: | Journal article |
Ngôn ngữ: | English |
Được phát hành: |
Springer Nature
2024
|
Những quyển sách tương tự
-
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
Bằng: Kirk, HR, et al.
Được phát hành: (2022) -
Is more data better? re-thinking the importance of efficiency in abusive language detection with transformers-based active learning
Bằng: Kirk, HR, et al.
Được phát hành: (2022) -
Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate
Bằng: Kirk, H, et al.
Được phát hành: (2021) -
Exploring large language models for ontology alignment
Bằng: He, Y, et al.
Được phát hành: (2023) -
Survey on large language models alignment research
Bằng: LIU Kunlin, et al.
Được phát hành: (2024-06-01)