← all papers · overview

Improving LLM Predictions Via Inter-layer Structural Encoders

Abstract

The standard practice in Large Language Models (LLMs) is to base predictions on the final-layer token representations. Recent studies, however, show that intermediate layers encode substantial information, which may contain more task-relevant features than the final-layer representations alone. Importantly, it was shown that for different tasks, different layers may be optimal. In this work we int

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).