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.
Anisotropy
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4representative citing papers
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
RSRank learns calibrated relevance scores from alignment between representational shifts induced by candidate documents and those from oracle document sets, enabling zero-threshold filtering.
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
citing papers explorer
No citing papers match the current filters.