MMLU Benchmark

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

• MMLU Promethod0.830
  General knowledge benchmark across domains (1400 subsampled problems) used to evaluate capability preservation
• We hypothesize that degraded generalization on benchmarks like MMLU may reflect the computational demands of the tasks.hypothesis0.771
  Connecting the paper's task-difficulty findings to prior observations of weak generalization on complex QA benchmarks.
• AILuminate Benchmarkmethod0.767
  Comprehensive AI safety benchmark evaluating resistance to harmful prompts across hazard categories; used in Experiment 1
• InCharacter Benchmarkframework0.732
  Benchmark used to evaluate personality fidelity in RPAs through psychological interviews with abstract Big Five questions
• Werewolf benchmarkframework0.731
  LLM benchmark on the communication game Werewolf, cited.
• Multi-layer Perceptron (MLP)method0.727
  Feed-forward neural network with hidden layers, capable of representing non-linearly separable functions.
• HaluEval Benchmarkmethod0.723
  External hallucination benchmark used to validate trait expression scores beyond the paper's own evaluation questions
• consciousness benchmarksconcept0.718
  Benchmarks designed to evaluate AI consciousness, which the paper argues are vulnerable to eval awareness inflation.