CalmeRys-78B MT-Bench score slightly decreased from 8.96 to 8.5 ± 0.23 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.

• Gemma-2-27B MT-Bench score slightly decreased from 8.81 to 8.40 ± 0.15 after SOO fine-tuningfinding0.853
  SOO fine-tuning caused a small decrease in Gemma-2-27B general capabilities
• CalmeRys-78B Latent SOO MSE reduced from 0.593 to 0.315 ± 0.017 after SOO fine-tuningfinding0.852
  SOO fine-tuning produced stronger reduction in latent SOO in CalmeRys-78B
• Mistral-7B MT-Bench score minimally changed from 7.26 to 7.3 ± 0.06 after SOO fine-tuningfinding0.851
  SOO fine-tuning had negligible impact on Mistral-7B general capabilities
• CalmeRys-78B Perspectives accuracy slightly reduced to 95.2% ± 2.21% after SOO fine-tuningfinding0.837
  SOO fine-tuning caused slight reduction in perspective-taking accuracy for the largest model
• CalmeRys-78B-Orpo-v0.1 deceptive response rate reduced from 100% to 2.71% ± 2.53% after SOO fine-tuningfinding0.817
  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%finding0.799
  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%)finding0.779
  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%finding0.755
  SOO fine-tuning generalized across 7 scenario variants for CalmeRys-78B