Conceptio
›
Archive
›
arXiv (All)
arXiv (All)
open access
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
Aamir, Saad et al.
arXiv (All) · Papers · License: Open Access
Open Source ↗
Direct PDF ↓
computation-and-language
computation and language, machine learning
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
#1052296
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
#1052293
Density-Ratio Rescoring for Imbalanced Classification Using Raking Duals and Classifier Scores
#1052300
Record
· ID 1011284
Retrieved via
Conceptio
— every document is proof-bundled with source, license, and retrieval metadata.