Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Joachim Diederich
We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule…
cs.AI2025
Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis
Joachim Diederich
The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic a…