2 papers
cs.LG2025
Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
Grgur KovaÄ, Jérémy Perez, Rémy Portelas +2
Large language models (LLMs) are increasingly used in the creation of online content, creating feedback loops as subsequent generations of models will be trained on this synthetic…
cs.CL2024
Stick to your Role! Stability of Personal Values Expressed in Large Language Models
Grgur KovaÄ, Rémy Portelas, Masataka Sawayama +2
The standard way to study Large Language Models (LLMs) with benchmarks or psychology questionnaires is to provide many different queries from similar minimal contexts (e.g. multipl…