9 citations · 25 across the 8 of their papers we have counts for
8 papers
Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
Grgur Kovač, 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…
When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
Jérémy Perez, Grgur Kovač, Corentin Léger +5
As large language models (LLMs) start interacting with each other and generating an increasing amount of text online, it becomes crucial to better understand how information is tra…
Stick to your Role! Stability of Personal Values Expressed in Large Language Models
Grgur Kovač, 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…
The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents
Grgur Kovač, Rémy Portelas, Peter Ford Dominey +1
Developmental psychologists have long-established the importance of socio-cognitive abilities in human intelligence. These abilities enable us to enter, participate and benefit fro…
Large Language Models as Superpositions of Cultural Perspectives
Grgur Kovač, Masataka Sawayama, Rémy Portelas +3
Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with…
SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
Grgur Kovač, Rémy Portelas, Katja Hofmann +1
Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. Within the Deep Reinforcement Learning (DRL) fi…
SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
Grgur Kovač, Rémy Portelas, Katja Hofmann +1
Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. This problem motivated many research directions…
GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning
Grgur Kovač, Adrien Laversanne-Finot, Pierre-Yves Oudeyer
Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity…