MACPO: weak-to-strong alignment via multi-agent contrastive preference optimization
- Author(s):
- Lyu, Y.; Yan, L.; Wang, Z.; Yin, D.; Ren, P.; Rijke, M. de; Ren, Z. (0000-0002-9076-6565)
- Published
- 2025
- Publication type
- Article in monograph or in proceedings
- Date issued
- 2025-04-24
- Language
- English
- Is part of
- The Thirteenth International Conference on Learning Representations ICLR 2025 (2025), p. 63022--63048
- hdl
- 1887/4306656
- URL
- https://proceedings.iclr.cc/paper_files/paper/2025/file/9ddd47ee8d0b9543925a8db3e9d879b3-Paper-Conference.pdf
Conference
- Meeting name
- International Conference on Learning Representations 2025
- Meeting location
- Singapore, Singapore
- Meeting date
- 2025-04-24 - 2025-04-28
