A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.
Disentangling latent shifts of in-context learning with weak supervision.arXiv preprint arXiv:2410.01508, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.