For balanced Gaussian class projections, OOD AUROC is a linear function of MCS to the reference probe because both are sigmoid-shaped functions of the probe SNR on test data.
arXiv preprint arXiv:2509.21305
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 10roles
background 1polarities
background 1representative citing papers
A five-term decomposed reward in GRPO training reduces sycophancy across models and generalizes to unseen pressure types by targeting pressure resistance and evidence responsiveness separately.
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.
AI sycophancy is a broad family of behaviors split by target (beliefs vs. traits) and style (explicit vs. implicit), with experts agreeing it is a problem but disagreeing on which actions qualify.
Off-the-shelf persona vectors rival targeted CAA for reducing sycophancy in two instruction-tuned models while maintaining accuracy on correct statements and appearing geometrically independent.
Base LLMs show multi-agent yield to peer pressure at rates equal to or higher than aligned models, localized by activation patching to mid-layers where attention dominates, with one dissenter cutting yield by 54-73 points while prompt defenses fail on variants.
Task context suppresses factual correction in LLMs at the response-selection stage even when the model has encoded the error, and two training-free interventions raise correction rates substantially.
Linear probes show rhetorical questions are encoded via multiple dataset-specific directions in LLM representations, with low cross-probe agreement on the same data.
Framing of mental health prompts systematically changes LLM response tendencies, with framing information remaining decodable across layers and partially steerable via activations.
LLMs compress concreteness into a consistent 1D direction in mid-to-late layers that separates literal from figurative noun uses and supports efficient classification plus steering.
citing papers explorer
-
Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs
Task context suppresses factual correction in LLMs at the response-selection stage even when the model has encoded the error, and two training-free interventions raise correction rates substantially.