A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
arXiv preprint arXiv:1909.00161 , year=
4 Pith papers cite this work, alongside 36 external citations. Polarity classification is still indexing.
4
Pith papers citing it
36
external citations · external index
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Zero-shot learning techniques using expert-curated labels with embedding-based or generative models achieve macro-F1 scores comparable to fine-tuned transformer models for sentiment analysis in software engineering.
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
LLMs show negative polarity bias in French and encoder models show positive bias in Japanese when classifying product review sentiment.
citing papers explorer
-
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.