The paper proposes that creativity in large language models can be measured by performance on the long tail of a reference input-output distribution, using n‑gram absence from pretraining data as a novelty proxy. Across 15 benchmarks and 26 open‑weight models, the authors find that creativity benchmarks occupy further tail regions than standard benchmarks and that higher‑tail subsets better align with human creativity judgments. They introduce a new diagnostic, q@Tail(α), to assess mean task quality on the tail fraction of existing benchmarks, revealing significant potential for improving LLM creativity through stronger tail performance.
By Yichen Wang, Tenghao Huang, Vishakh Padmakumar, Mina Lee
Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks.
arXiv:2606. 11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential.
By Min Sen Tan, Zachary Kit Chun Choy, Syed Ali Redha Alsagoff, Nadya Yuki Wangsajaya, Mohor Banerjee, Swaagat Bikash Saikia, Alvin Chan
arXiv:2510. 20091v3 Announce Type: replace-cross Abstract: Creativity is often seen as a hallmark of human intelligence.
By Zhaoyi Joey Hou, Bowei Alvin Zhang, Yining Lu, Bhiman Kumar Baghel, Anneliese Brei, Ximing Lu, Meng Jiang, Faeze Brahman, Snigdha Chaturvedi, Haw-Shiuan Chang, Daniel Khashabi, Xiang Lorraine Li
The paper introduces Think‑Probe‑Respond (TPR), a lightweight method to improve large language models’ ability to judge the novelty of research ideas. It identifies a systematic bias where models tend to label ideas as "medium novel" despite generating human‑like rationales, and shows that probing hidden states during reasoning and conditioning the final response on these probes boosts novelty judgment accuracy by 22.30%. TPR effectively reduces the medium‑novelty bias across strong baseline models.
By Tim Schopf, Tobias Schreieder, Akiko Aizawa
arXiv:2610.02022v2 Announce Type: replace
Abstract: AI-based ideation systems are often evaluated on the novelty of their ideas, and that judgment is increasingly delegated to large language models....
By Noy Sternlicht, Simra Shahid, Peter Jansen, Daniel S. Weld, Pao Siangliulue, Tom Hope