Probe Generalization as Subspace Selection for OOD Deception Detection
Source
Daniel Yoo, Adrians Skapars
Author
Daniel Yoo, Adrians Skapars
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Deception probes built for one task often fail on new ones. Filtering to the components that encode the deception concept abstractly, rather than dataset-specific surface features, is a concrete way to make monitoring tools transfer across domains.
articleMemorization Diagnostics for Code LLMs Should be Scale-AwarePrateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djir\'e, Xunzhu Tang, Yewei Song, Iyiola Emmanuel Olatunji, El Hacen Diallo, Jacques Klein, Tegawend\'e F. Bissyand\'e
articleDude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy DetectionWeijie Liu, Running Zhao, Wenhao Yuan, Jinfeng Xu, Zhanfeng Xu, Xiaoxi Zhang, Edith Cheuk-Han Ngai
articleCompiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem ProvingZhuo Liu, Ding Yu, Hangfeng He