conftrace_

layer-wise pooling

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

layer-wise attention (1) latent geometry (1) cluster divergence (1) davies-bouldin score (1) attention pooling (1) jailbreak detection (1) alignment quality (1) semantic textual similarity (1) sentence representation (1) pre-trained language model (1)

Papers

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations EMNLP 2025 Don’t Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling COLING 2022