2 citations · 3 across the 9 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
Jianhao Zhang, Ou Wu, Yi Du
Catastrophic forgetting is a central obstacle in single-stage fine-tuning of large language models (LLMs) on a new task, especially when the original pretraining data are unavailab…
cs.LG2026
Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Instruction Tuning
Can Wu, Xinrui Chen, Ou Wu +1
Token selection for instruction tuning is coupled: supervision utility depends on retained context, and vice versa. Existing methods largely optimize prompt compression or response…