arxiv
PublishedApril 18, 2026 at 4:00 AM
—neutral
Correcting Suppressed Log-Probabilities in Language Models with Post-Transformer Adapters
Publisher summary· verbatim
arXiv:2604.14174v1 Announce Type: cross Abstract: Alignment-tuned language models frequently suppress factual log-probabilities on politically sensitive topics despite retaining the knowledge in their hidden representations. We show that a 786K-parameter (approximately 0.02% of the base model) post-
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning17harxivProactive Service Agents: A Unified Decision Framework, Methods, and Evaluation17harxivX-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System17harxivA Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors17hThe Bubble Brief
WEEKLYRead language models insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗