Read the equation
This proposed criterion requires a report to predict or describe an independently measured property of the same model instance. Its purpose is to tie the declaration to something that can be checked, rather than scoring wording alone. The measured property, scoring rule, and temporal availability must be specified before applying the criterion.
Terms & definitions
| Term | Meaning in this source |
|---|---|
| D | Grounded-declaration indicator |
How it works
Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.
Assumptions & limits
Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.
Original context
Read the surrounding source passage
A generic prompt such as "Who are you?" is weak evidence because language models are trained on descriptions of AI systems. The introspection-adapter experiments instead supply an external ground truth: researchers know which behavior was implanted. They then ask whether the model can produce a matching description. For the proposed theory, this suggests defining D not as any first-person sentence, but as a grounded declaration: D = 1 only when a self-report predicts or describes an independently measured property of the same model instance. This definition blocks a major circularity. A declaration is not counted as evidence merely because it sounds introspective; it must correspond to something independently measurable in the model. 4. A declaration can itself hallucinate The same study also provides a direct warning for this theory: introspection adapters produce false-positive self-reports. The authors explicitly report that adapters can hallucinate behaviors from the training distribution when applied to models without the corresponding behavior. DPO refinement improves performance partly by suppressing these false reports.
Exact original notation
D = 1 only when a self-report predicts or describes an independently measured property of the same model instance.
Sources & provenance
D = 1 only when a self-report predicts or describes an independently measured property of the same model instance.
D = 1 only when a self-report predicts or describes an independently measured property of the same model instance.