Evidence record 18844 · automatically gathered

Self-referential consistency in stateless language models: a behavioral perspective

Large language models (LLMs) increasingly generate outputs that resemble introspection, including self-reference, epistemic modulation, and claims about their internal states. This study investigates whether such behaviors reflect stable underlying patterns or merely surface-level generative artifacts. We evaluated five open-weight, stateless LLMs using a structured battery of 21 introspective prompts. The main corpus comprised 1050 completions collected under a baseline decoding condition ( tem

Record details

Published: 12 August 2026
Source: AI & Society
Category: Research
Topics: Finance, VC & PE
Retrieved: 13 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (12 August 2026), “Self-referential consistency in stateless language models: a behavioral perspective,” evidence record 18844, https://ethics.ai/record/18844 (originally published by AI & Society).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.