Different scoring mechanisms cause encoder-based authorship attribution models to consolidate authorship signals at different layers, as shown by causal interventions and gradient analysis.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
An 8B autoregressive LM implements a language-switching backdoor via a three-phase circuit with early trigger composition, orthogonal mid-layer propagation, and final-layer MLP conversion, routed through a single-position serial bottleneck.
citing papers explorer
-
Where Does Authorship Signal Emerge in Encoder-Based Language Models?
Different scoring mechanisms cause encoder-based authorship attribution models to consolidate authorship signals at different layers, as shown by causal interventions and gradient analysis.
-
Language-Switching Triggers Take a Latent Detour Through Language Models
An 8B autoregressive LM implements a language-switching backdoor via a three-phase circuit with early trigger composition, orthogonal mid-layer propagation, and final-layer MLP conversion, routed through a single-position serial bottleneck.