Ghosted Layers recovers accuracy in layer-pruned LLMs via a closed-form unconstrained linear operator that aligns boundary activations using a small calibration set.
Can a suit of armor conduct electricity? a new dataset for open book question answering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Code-Guided Reasoning protocol reports a 28 percentage-point macro accuracy gain for small language models on MCQA when using generated executable Python scaffolds versus direct answering on 20k+ items.
citing papers explorer
-
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
Ghosted Layers recovers accuracy in layer-pruned LLMs via a closed-form unconstrained linear operator that aligns boundary activations using a small calibration set.
-
Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds
Code-Guided Reasoning protocol reports a 28 percentage-point macro accuracy gain for small language models on MCQA when using generated executable Python scaffolds versus direct answering on 20k+ items.