Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering
Can a language model estimate its familiarity with an entity before generating an answer? We study activations at the final prompt token in twelve instruction-tuned models from the Bielik, PLLuM, Gemma-4, and Qwen3 families, using a new dataset of 1,440 Polish entities spanning four domains and ten Wikipedia-pageview deciles, plus fabricated controls. Familiarity-probe scores separate real from fabricated entities in every family; in the Polish-adapted Bielik and PLLuM families they additionally track entity popularity (model-mean Spearman $ρ$ 0.28-0.57, versus at most 0.11 in Gemma-4 and Qwen
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%Evaluating J-space entropy as an error predictor across 7 datasets on Qwen3-4B [R] →
- PossiblePossibly related (embedding) · 46%Large Language Models Are Still Getting Stronger, but Researchers Face New Bottlenecks in Data, Evaluation, and Safety | Newswise - Newswise →
- LinkedLinked via arxiv author · 85%Grzegorz Brzezinka →
“Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steerin”