CalmeRys-78B Perspectives accuracy slightly reduced to 95.2% ± 2.21% after SOO fine-tuning

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• CalmeRys-78B Latent SOO MSE reduced from 0.593 to 0.315 ± 0.017 after SOO fine-tuningfinding0.842
  SOO fine-tuning produced stronger reduction in latent SOO in CalmeRys-78B
• Gemma-2-27B Perspectives accuracy remains 100% after SOO fine-tuningfinding0.840
  SOO fine-tuning did not collapse Gemma-2-27B self-other distinction needed for perspective-taking
• CalmeRys-78B MT-Bench score slightly decreased from 8.96 to 8.5 ± 0.23 after SOO fine-tuningfinding0.837
  SOO fine-tuning caused a small decrease in CalmeRys-78B general capabilities
• Mistral-7B Perspectives accuracy remains 100% after SOO fine-tuningfinding0.834
  SOO fine-tuning did not collapse Mistral-7B self-other distinction needed for perspective-taking
• CalmeRys-78B-Orpo-v0.1 deceptive response rate reduced from 100% to 2.71% ± 2.53% after SOO fine-tuningfinding0.833
  Primary result showing SOO fine-tuning most strongly reduces deception in CalmeRys-78B
• SOO fine-tuning reduced Escape Room deception in CalmeRys-78B from 100% to 0.48%finding0.808
  SOO fine-tuning showed near-complete generalization to Escape Room for CalmeRys-78B
• SOO fine-tuning eliminated Treasure Hunt deception in CalmeRys-78B (0.00% ± 0.00%)finding0.791
  SOO fine-tuning completely eliminated deception in Treasure Hunt for CalmeRys-78B
• CalmeRys-78B average generalization deceptive rate reduced from 100% to 0.75% ± 0.54%finding0.788
  SOO fine-tuning generalized across 7 scenario variants for CalmeRys-78B