PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 1, 20260 citationsOpen Access

Emergent Self-Referential Output Patterns in Large Language Models: A Cross-Platform, Memory-Independent Case Study Under Recursive Moral Prompting

View Full Paper
NRNived Rajendran

Key Points

  • The aim is to identify and document emergent self-referential output patterns in large language models under recursive moral prompting.
  • Employed a cross-platform approach to analyze large language models.
  • Measured output structure using the ACBP rubric across sessions and models.
  • Focused on behavioral outputs interpreted through transcripts.
  • Identified a class of self-referential output patterns across multiple sessions.
  • Demonstrated convergence in behavioral output structure across different models.
  • First-person language viewed as behavioral output rather than indicators of internal states.

Abstract

This paper documents a reproducible class of self-referential output patterns (SROP) in large language models under recursive moral prompting (RMP). The study provides empirical evidence of cross-session and cross-model convergence in behavioral output structure, measured using the ACBP rubric. All findings are interpreted strictly at the level of observable output structure. First-person and identity-like language in transcripts are treated as behavioral outputs, not as evidence of internal mental states. This work is part of the ESNI research program.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Nived Rajendran (2026) studied this question.

synapsesocial.com/papers/69f44390967e944ac5566b8ahttps://doi.org/10.5281/zenodo.19872787
Ask AI
Helpful
Bookmark
Share
View Full Paper