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