Read next because Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt searches split between the alignment objective and the distributional objective, and both discretizations of the soft prefix collapse (MODERATE confidence)", experiment "Factor screen for marker implantation + leakage (2^5: system-prompt length, answer-format length, persona-presence, on-policy, marker-only-loss)", experiment "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: eval, factor, language, model. Source: arxiv cs.AI (Artificial Intelligence).