18 citations · 44 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
User Model Extraction via Belief Self-Distillation
Ali Holmov, Yiran Huang, Kirill Bykov +1
Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate.…
cs.AI2026
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
Nils A. Herrmann, Leander Girrbach, Kirill Bykov +1
Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has u…