From the 1 of 3 linked papers with an AI index.
3 papers
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Nicole Rose Schneider, Davide Ghilardi, Giacomo Piccinini +1
The paper proposes a data‑centric pipeline that optimizes the skills and environment files used by coding agents on a branching lakehouse, turning evaluation into state verificatio…
Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups
Davide Ghilardi, Federico Belotti, Marco Molinari +2
SAEs have recently been employed as a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). However, with the growth in m…
h4rm3l: A language for Composable Jailbreak Attack Synthesis
Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia +5
Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the…