Measuring LLM Novelty As The Frontier Of Original And High-Quality Output

ICLR 2026 Conference Submission19977 Authors

Keywords: generation, evaluation, memorization, novelty, benchmark, creativity

TL;DR: We quantify and evaluate the novelty in LLM generations as the harmonic mean of the n-gram originality and output quality, and analyse how model scale, training methods and inference methods impact it.

Abstract: As large language models (LLMs) are increasingly used for ideation and scientific discovery, it is important to evaluate their ability to generate novel output. Prior work evaluates novelty as originality with respect to model training data, but original outputs can be of low quality. In contrast, non-expert judges more reliably score quality but may favor memorized outputs, limiting the reliability of human preference as a metric. We introduce a new novelty metric for LLM generations that balances originality and quality---the harmonic mean of the fraction of \ngrams unseen during training and a task-specific quality score. Using this framework, we identify trends that affect the novelty of generations from three families of open-data models (OLMo, OLMo-2, and Pythia) on three creative tasks---story completion, poetry writing, and creative tool use. We find that model-generated text from some base LLMs is less novel than human-written text from the internet. However, increasing model scale (OLMo 1B to 7B to 32B) and post-training reliably improves novelty due to improvements in output quality. We also find that improving the base model at the same scale (\eg OLMo 7B to OLMo-2 7B) leads to higher novelty due to higher originality. Finally, we observe that inference-time methods, such as prompting and providing novel in-context examples, have a much smaller effect on novelty, often increasing originality at the expense of quality. This highlights the need for further research into more effective elicitation strategies as we use models for creative applications.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 19977