# Can LLMs capture stable human-generated sentence entropy measures?

arXiv: https://arxiv.org/abs/2602.04570 · HTML: https://mlsanity.com/paper/2602.04570/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 7 of 7)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [Probabilistic Predictions of People Perusing: Evaluating Metrics of Language Model Performance for Psycholinguistic Modeling](https://mlsanity.com/paper/2009.03954/) (2020)
- [Humans and language models diverge when predicting repeating text](https://mlsanity.com/paper/2310.06408/) (2023)
- [Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned](https://mlsanity.com/paper/2410.12057/) (2024)

## Built on by (most cited first, 1 of 1)

- [On the scaling relationship between cloze probabilities and language model next-token prediction](https://mlsanity.com/paper/2602.17848/) (2026)

## Abstract (arXiv)

Predicting upcoming words is a core mechanism of language comprehension and may be quantified using Shannon entropy. There is currently no empirical consensus on how many human responses are required to obtain stable and unbiased entropy estimates at the word level. Moreover, large language models (LLMs) are increasingly used as substitutes for human norming data, yet their ability to reproduce stable human entropy remains unclear. Here, we address both issues using two large publicly available cloze datasets in German 1 and English 2. We implemented a bootstrap-based convergence analysis that tracks how entropy estimates stabilize as a function of sample size. Across both languages, more than 97% of sentences reached stable entropy estimates within the available sample sizes. 90% of sentences converged after 111 responses in German and 81 responses in English, while low-entropy sentences (<1) required as few as 20 responses and high-entropy sentences (>2.5) substantially more. These findings provide the first direct empirical validation for common norming practices and demonstrate that convergence critically depends on sentence predictability. We then compared stable human entropy values with entropy estimates derived from several LLMs, including GPT-4o, using both logit-based probability extraction and sampling-based frequency estimation, GPT2-xl/german-GPT-2, RoBERTa Base/GottBERT, and LLaMA 2 7B Chat. GPT-4o showed the highest correspondence with human data, although alignment depended strongly on the extraction method and prompt design. Logit-based estimates minimized absolute error, whereas sampling-based estimates were better in capturing the dispersion of human variability. Together, our results establish practical guidelines for human norming and show that while LLMs can approximate human entropy, they are not interchangeable with stable human-derived distributions.