List your company

Theory-of-Mind Reasoning on apartment seen

87Belief Inference Accuracy8B ↬ 405B
80.03281.84183.6585.459Jun 2, 2025

Evaluation results

MethodLinks
8B ↬ 405BSolution Type=Ours, Backbone=Llama3.1, Scaling Setting=weak-to-strong control2025.06877781.3
8B ↬ 70BSolution Type=Ours, Backbone=Llama3.1, Scaling Setting=weak-to-strong control2025.0685.674.679.3
70B-post-trainedSolution Type=Raw, Backbone=Llama3.1, Scaling Setting=direct post-training2025.06856271.8
4B-depth ↬ 70BSolution Type=Ours, Backbone=Llama3.1, Scaling Setting=weak-to-strong control2025.0684.673.678.3
4B-wide ↬ 70BSolution Type=Ours, Backbone=Llama3.1, Scaling Setting=weak-to-strong control2025.0683.674.678.5
70B-zero-shotSolution Type=Raw, Backbone=Llama3.1, Scaling Setting=zero-shot2025.0680.356.366.6