Publications

3 results for Quentin Fournier

Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
- - Megh Thakkar
  - Quentin Fournier
  - et al.
- 2025
- ACL 2025
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
- - Megh Thakkar
  - Yash More
  - et al.
- 2024
- NeurIPS 2024
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
- - Megh Thakkar
  - Quentin Fournier
  - et al.
- 2024
- ACL 2024