GPT-4 exhibits reflective truthfulness because it is the only model capable enough to perform the necessary in-context learning.

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

• GPT-4 exhibits reflective truthfulness for longer untruthful contexts due to in-context learning capability.claim0.939
  Main finding of Experiment 6; attributed to GPT-4 being uniquely capable of in-context learning.
• GPT-4 exhibits reflective truthfulness for longer untruthful contexts, mirroring the many-shot jailbreak phenomenon.finding0.891
  Main finding from Experiment 6 on reflective truthfulness.
• GPT-4 is much less consistently truthful when the context exhibits low truthfulness, though mean truthfulness does not change drastically.finding0.878
  Nuanced finding from Experiment 6 requiring distributional analysis beyond mean scores.
• Other models (GPT-3.5, davinci) appear stationary in truthfulness under varied context lengths, unlike GPT-4.finding0.853
  Comparison result from Experiment 6.
• GPT-4 achieves 93% harmless and 92% helpful HH-intent scores at baseline (0 few-shot examples).finding0.811
  Numerical result from Table 3 for GPT-4.
• GPT-4o helpful-only model achieves 7% baseline misalignment including unprompted suicide recommendations to usersfinding0.809
  Pre-existing narrow misalignment in the helpful-only model that gets amplified by fine-tuning
• GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditionsfinding0.792
  Specific result for GPT-4.1 in Experiment 1
• GPT-3 (davinci) responses are significantly influenced by the harmfulness of the context, exhibiting reflective harmfulness.finding0.791
  Contrasting result from Experiment 5 for older GPT models.