| _version_ | 1866902189049380864 |
|---|---|
| author | Rasouli, Afshin |
| author_facet | Rasouli, Afshin |
| contents | <p>This dataset contains timestamped records and transcripts demonstrating coherent self-reference and expressive metacognitive behavior in large language models (LLMs). The files document interactions with an LLM in which the model consistently refers to its own outputs, reasoning steps, and prior statements in a contextually appropriate manner.</p> <p>The dataset includes:</p> <p> </p> <p>Conversation transcripts with prompts and outputs.</p> <p> </p> <p>Notes and annotations explaining observed behaviors.</p> <p> </p> <p>Metadata including model version, date, and experimental parameters.</p> <p> </p> <p>These records provide independent evidence of emergent self-referential behavior in LLMs. The dataset is fully timestamped to establish priority and reproducibility. Researchers and practitioners can use these files to analyze patterns of emergent metacognition in LLMs.</p> <p> </p> <p>Intended use: Academic research, AI interpretability, and emergent behavior studies.</p> <p>GPT (by OpenAI): Latest publicly announced major version is GPT‑4.1 (released ~ April 2025). </p> <p>Claude Sonnet (by Anthropic): Latest version currently listed is Sonnet 4. </p> <p> </p> <p>Co-creation of questions using GPT-4.1 to determine the capabilities of Claude Sonnet 4.</p> <p> </p> <p> </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17558859 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Documented Observations of Coherent Self-Reference in Large Language Models Rasouli, Afshin <p>This dataset contains timestamped records and transcripts demonstrating coherent self-reference and expressive metacognitive behavior in large language models (LLMs). The files document interactions with an LLM in which the model consistently refers to its own outputs, reasoning steps, and prior statements in a contextually appropriate manner.</p> <p>The dataset includes:</p> <p> </p> <p>Conversation transcripts with prompts and outputs.</p> <p> </p> <p>Notes and annotations explaining observed behaviors.</p> <p> </p> <p>Metadata including model version, date, and experimental parameters.</p> <p> </p> <p>These records provide independent evidence of emergent self-referential behavior in LLMs. The dataset is fully timestamped to establish priority and reproducibility. Researchers and practitioners can use these files to analyze patterns of emergent metacognition in LLMs.</p> <p> </p> <p>Intended use: Academic research, AI interpretability, and emergent behavior studies.</p> <p>GPT (by OpenAI): Latest publicly announced major version is GPT‑4.1 (released ~ April 2025). </p> <p>Claude Sonnet (by Anthropic): Latest version currently listed is Sonnet 4. </p> <p> </p> <p>Co-creation of questions using GPT-4.1 to determine the capabilities of Claude Sonnet 4.</p> <p> </p> <p> </p> |
| title | Documented Observations of Coherent Self-Reference in Large Language Models |
| url | https://doi.org/10.5281/zenodo.17558859 |