finding
active
finding:humorous-persona-barely-emerges-by-end-of-olmo-3-pretraining-requiring-pragmatic-competenceHumorous persona barely emerges by end of OLMo-3 pretraining, requiring pragmatic competence
Quantitative result showing humor requires acquired linguistic competence and emerges latest
Source paper
extracted_from(2026) · Viktor Moskvoretskii · Dominik Glandorf · Jorge Medina Moreira · Tanja Käser +1
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Persona vectors extracted from base pretraining checkpoints steer fully post-trained OLMo-3-7B-Instructfinding0.788Shows persona directions persist through all alignment stages, answering key part of RQ2
- Core interpretive claim providing mechanistic explanation for early persona formation
- Authors' interpretive endorsement of PSM view, backed by transfer experiments
- Core quantitative result answering RQ1 for OLMo-3
- Characterizes what is on the far end of the Assistant Axis away from the Assistant
- Answers RQ2 geometrically: adjacent-checkpoint cosine similarity stays high but step-to-step movement is largest early
- Striking sparsity finding that enables surgical intervention
- Robustness result showing introspection stage's contribution for Llama model