3 papers
cs.CR2026
BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
Leonhard Waibl, Felix Michalak, Hadrien Mariaccia
LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI applications, yet existing benchmar…
cs.AI2026
Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
Florian Dietz, William Wale, Oscar Gilg +5
Detecting misalignment in large language models is challenging because models may learn to conceal misbehavior during training. Standard auditing techniques fall short: black-box m…
cs.LG2025
Some Attention is All You Need for Retrieval
Felix Michalak, Steven Abreu
We demonstrate complete functional segregation in hybrid SSM-Transformer architectures: retrieval depends exclusively on self-attention layers. Across RecurrentGemma-2B/9B and Jamb…