Repeated self-referential questions to Gemini produce semantically less stable answers (instability 0.343) than unresolvable philosophy (0.192) or verifiable questions (0.105).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
Repeated self-referential questions to Gemini produce semantically less stable answers (instability 0.343) than unresolvable philosophy (0.192) or verifiable questions (0.105).