Portrait of Aurélien Bück-Kaeffer

Aurélien Bück-Kaeffer

Master's Research - McGill University
Supervisor
Reihaneh Rabbany
Research Topics
AGI (Artificial General Intelligence)
AI Alignment
AI Ethics
Applied Machine Learning
Deep Learning
Deep Neural Networks
Generative Models
Large Language Models (LLM)
Multimodal Learning
Natural Language Processing
Neural Networks
Optimization
Reinforcement Learning
GitHub

Publications

EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations
Sneheel Sarangi
Maximilian Puelma Touzel
Aurélien Bück-Kaeffer
Zachary Yang
Jean-François Godbout
Reihaneh Rabbany
LLMs are increasingly deployed to simulate social interactions, yet many of the existing simulators remain ad hoc and monolithic. This lack … (see more)of architectural standardization prevents reproducible research and complicates downstream evaluation. We advance a rigorous science of LLM-based multi-agent simulation by modularizing core components into Environments, Agents, Simulation engines, and Evaluation metrics (EASE). We demonstrate the utility of EASE configuration by wrapping it in an experimental study schema for orchestrating workflows centered around answering explicit research questions in generated scenarios. We contribute SiliSocS, an open-source, research-ready Silicon Society Sandbox implementing a study-structured EASE configuration to enable highly configurable and reproducible LLM-based social simulations. Using SiliSocS and EASE, we present three case studies, showcasing the system's comprehensive assessment of existing questions, ability to dive deeper into complex questions, and elaboration of existing studies, respectively. Together, these case studies highlight the limitations of current modeling approaches and isolate the impacts of design choices on key results.
2026-05-27
arXiv (preprint)
doi.org
arxiv.org
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
Aurélien Bück-Kaeffer
Sneheel Sarangi
Maximilian Puelma Touzel
Reihaneh Rabbany
Zachary Yang
Jean-François Godbout
Studies attempting to simulate human behavior with …
2026-04-29
arXiv (preprint)
doi.org
arxiv.org
Position: Time to Close The Validation Gap in LLM Social Simulations
Maximilian Puelma Touzel
Sneheel Sarangi
Aurélien Bück-Kaeffer
Zachary Yang
Jean-François Godbout
Reihaneh Rabbany
LLM-based social simulations—in which many language model agents interact over multiple turns—are rapidly proliferating across policy an… (see more)alysis, epidemiology, and computational social science. Yet the field lacks consensus on how to validate these simulations, with evaluation methods that are sparse, inconsistent, and rarely shared across disciplinary silos. We argue this creates a serious risk: premature deployment of unvalidated simulators in high-stakes domains. Our position is that the field must pivot from expansion to consolidation, prioritizing methodological standardization—shared benchmarks, open data, and reproducible evaluation protocols grounded in social science and complex systems research. We outline a concrete research program organized around specific learning problems/benchmarks, providing a path toward answering the fundamental question: when are LLM social simulations useful modelling objects?
2025-12-31
International Conference on Machine Learning (Accept (regular))
openreview.net
openreview.net
$\texttt{BluePrint}$: A Social Media User Dataset for LLM Persona Evaluation and Training
Aur'elien Buck-Kaeffer
Je Qin Chooi
Dan Zhao
Maximilian Puelma Touzel
Kellin Pelrine
Jean-François Godbout
Reihaneh Rabbany
Zachary Yang
Large language models (LLMs) offer promising capabilities for simulating social media dynamics at scale, enabling studies that would be ethi… (see more)cally or logistically challenging with human subjects. However, the field lacks standardized data resources for fine-tuning and evaluating LLMs as realistic social media agents. We address this gap by introducing SIMPACT, the SIMulation-oriented Persona and Action Capture Toolkit, a privacy respecting framework for constructing behaviorally-grounded social media datasets suitable for training agent models. We formulate next-action prediction as a task for training and evaluating LLM-based agents and introduce metrics at both the cluster and population levels to assess behavioral fidelity and stylistic realism. As a concrete implementation, we release BluePrint, a large-scale dataset built from public Bluesky data focused on political discourse. BluePrint clusters anonymized users into personas of aggregated behaviours, capturing authentic engagement patterns while safeguarding privacy through pseudonymization and removal of personally identifiable information. The dataset includes a sizable action set of 12 social media interaction types (likes, replies, reposts, etc.), each instance tied to the posting activity preceding it. This supports the development of agents that use context-dependence, not only in the language, but also in the interaction behaviours of social media to model social media users. By standardizing data and evaluation protocols, SIMPACT provides a foundation for advancing rigorous, ethically responsible social media simulations. BluePrint serves as both an evaluation benchmark for political discourse modeling and a template for building domain specific datasets to study challenges such as misinformation and polarization.
2025-09-26
ArXiv (preprint)
doi.org
arxiv.org