Mapping Social Choice Theory to RLHF
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909175876943872 |
|---|---|
| author | Dai, Jessica Fleisig, Eve |
| author_facet | Dai, Jessica Fleisig, Eve |
| contents | Recent work on the limitations of using reinforcement learning from human feedback (RLHF) to incorporate human preferences into model behavior often raises social choice theory as a reference point. Social choice theory's analysis of settings such as voting mechanisms provides technical infrastructure that can inform how to aggregate human preferences amid disagreement. We analyze the problem settings of social choice and RLHF, identify key differences between them, and discuss how these differences may affect the RLHF interpretation of well-known technical results in social choice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13038 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mapping Social Choice Theory to RLHF Dai, Jessica Fleisig, Eve Artificial Intelligence Computers and Society Recent work on the limitations of using reinforcement learning from human feedback (RLHF) to incorporate human preferences into model behavior often raises social choice theory as a reference point. Social choice theory's analysis of settings such as voting mechanisms provides technical infrastructure that can inform how to aggregate human preferences amid disagreement. We analyze the problem settings of social choice and RLHF, identify key differences between them, and discuss how these differences may affect the RLHF interpretation of well-known technical results in social choice. |
| title | Mapping Social Choice Theory to RLHF |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2404.13038 |