Creative Thought Embeddings: A Framework for Instilling Creativity in Large Language Models
Bibliographic record
Abstract
Creative intelligence represents a critical frontier in artificial intelligence research. While modern large language models (LLMs) excel in logical reasoning and factual responses, they often produce outputs that are predictable and lack genuine originality. This paper introduces Creative Thought Embeddings (CTE), a framework that embeds a creative bias directly into the latent representations of LLMs. By integrating a structured, multi-phase process that mirrors human divergent thinking, beginning with brainstorming and followed by synthesis, CTE guides models to generate outputs that are more novel, surprising, and contextually rich. The effectiveness of CTE is demonstrated across domains including humor generation, narrative storytelling, and educational explanations. Evaluation results, which employ quantitative lexical metrics and GPT-4o–based automated scoring show that while baseline models may exhibit greater surface-level lexical diversity, CTE enhances deeper semantic novelty and creative coherence. Finally, the paper presents a comparative analysis with standard prompt engineering and chain-of-thought approaches, discusses the trade-offs, and offers recommendations for further research and implementation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.007 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".