Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds 文章

ArXiv CS.AI2026-08-14PAPERen作者: Lucia Mal\'i\v{c}kov\'a

详细信息

来源站点
ArXiv CS.AI
作者
Lucia Mal\'i\v{c}kov\'a
文章类型
PAPER
语言
en
发布日期
2026-08-14

摘要

arXiv:2608.13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically evaluating the cognitive plasticity of open-weight architectures when subjected to rigorous behavioral reprogramming. Our objective is to induce a proactive, Socratic conversational framework, characterized by high-frequency question generation under strictly constrained high-performance computing (HPC) conditions. Through a massively parallelized hyperparameter sweep comprising 405 HPC jobs, we define precise mathematical bounds for parameter-efficient fine-tuning (PEFT). We identify an architectural threshold at LoRA rank $r=16$ and demonstrate via extensive epoch ablation that generalization capacity strictly reaches its optimal convergence within an optimized training window of $e \in [2, 3]$ depending on dataset density (minimum validation loss of 0.919).