conftrace_

internal representation analysis

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

semantic dynamics (1) representational contrastive scoring (1) hidden-state observation (1) truthfulness classification (1) language model trustworthiness (1) hidden state dynamics (1) model trustworthiness (1) reliability assessment (1) large language model (1) jailbreak detection (1)

Papers

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring ACL 2026 Sampling-Free Uncertainty Quantification via Hidden State Dynamics in Language Models AAAI 2026 The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness ACL 2026