arXiv Machine Learning
The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Oct 1
LLM Persona Unlearning
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-...
arXiv AI
Aug 14
Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
Hugging Face Trending Papers
Aug 13
Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds
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.
arXiv AI
Aug 14
Synthetic Persona Pretraining: Alignment from Token Zero
arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.
arXiv AI
Oct 1
Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gen...
arXiv AI
Jun 9
Emergence of Context Characteristics Sensitivity in Large Language Models
arXiv:2606. 09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query.