Humans Linguistically Align to their Conversational Partners, and Language Models Should Too
- Rachel Ostrand
- Sara Berger
- 2024
- ICML 2024
Workshop paper
Publications
54 results at ICML 2024
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
- Swanand Ravindra Kadhe
- Farhan Ahmed
- et al.
- 2024
- ICML 2024
Workshop paperMasking in Molecular Graphs Leveraging Reaction Context
- Jiannan Yang
- Veronika Thost
- et al.
- 2024
- ICML 2024
Workshop paperHow Do Nonlinear Transformers Acquire Generalization-Guaranteed CoT Ability?
- Hongkang Li
- Meng Weng
- et al.
- 2024
- ICML 2024
Workshop paper