Grzegorz Brzezinka

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Natural Language Processing (1)

Papers (1)

Jul 8, 2026

Grzegorz Brzezinka5d ago

Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale

Entity familiarity and factual reliability in LLMs are distinct phenomena, with models showing high awareness of known entities yet rarely abstaining from incorrect answers.

Grzegorz Brzezinka

Interpretability & Mechanistic Interp Natural Language Processing

Search

Grzegorz Brzezinka

Publication activitypapers/week, last 8 weeks

Research focus

Papers (1)