#cognitive-models2 articles

2 articles

AINeutralarXiv – CS AI · 5d ago6/104

🧠

Cognitive models can reveal interpretable value trade-offs in language models

Researchers developed a framework using cognitive models from psychology to analyze value trade-offs in language models, revealing how AI systems balance competing priorities like politeness and directness. The study shows LLMs' behavioral profiles shift predictably when prompted to prioritize certain goals and are influenced by reasoning budgets and training dynamics.

AINeutralarXiv – CS AI · Feb 275/102

🧠

Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

Researchers propose using cognitive models and AI algorithms as templates for designing modular language agents that combine multiple large language models. The position paper formalizes agent templates that specify roles for individual LLMs and how their functionalities should be composed to solve complex problems beyond single model capabilities.