Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915302205292544 |
|---|---|
| author | Barman, Kristian González Lohse, Simon de Regt, Henk |
| author_facet | Barman, Kristian González Lohse, Simon de Regt, Henk |
| contents | We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLM). Drawing on social epistemology and pluralist philosophy of science, we suggest ways in which RHLF can be made more responsive to human needs and how we can address challenges along the way. The paper concludes with an agenda for change, i.e. concrete, actionable steps to improve LLM development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17482 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives? Barman, Kristian González Lohse, Simon de Regt, Henk Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLM). Drawing on social epistemology and pluralist philosophy of science, we suggest ways in which RHLF can be made more responsive to human needs and how we can address challenges along the way. The paper concludes with an agenda for change, i.e. concrete, actionable steps to improve LLM development. |
| title | Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives? |
| topic | Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2407.17482 |