# Once Upon a Time: Interactive Learning for Storytelling with Small Language Models

arXiv: https://arxiv.org/abs/2509.15714 · HTML: https://mlsanity.com/paper/2509.15714/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Implicit Representations of Meaning in Neural Language Models](https://mlsanity.com/paper/2106.00737/) (2021)
- [Teaching Large Language Models to Reason with Reinforcement Learning](https://mlsanity.com/paper/2403.04642/) (2024)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics](https://mlsanity.com/paper/1812.08092/) (2018)
- [The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities](https://mlsanity.com/paper/2408.13296/) (2024)
- [Anisotropy Is Inherent to Self-Attention in Transformers](https://mlsanity.com/paper/2401.12143/) (2024)
- [OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics](https://mlsanity.com/paper/2105.08920/) (2021)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models](https://mlsanity.com/paper/2405.09605/) (2024)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [Language acquisition: do children and language models follow similar learning stages?](https://mlsanity.com/paper/2306.03586/) (2023)
- [BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop](https://mlsanity.com/paper/2502.10645/) (2025)
- [Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization](https://mlsanity.com/paper/2306.09299/) (2023)
- [Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing](https://mlsanity.com/paper/2410.11462/) (2024)
- [BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?](https://mlsanity.com/paper/2310.16681/) (2023)
- [Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models](https://mlsanity.com/paper/2505.05970/) (2025)
- [Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations](https://mlsanity.com/paper/2508.21164/) (2025)

## Built on by (most cited first, 11 of 11)

- [Structural priors for data-efficient language learning](https://mlsanity.com/paper/2609.11505/) (2026)
- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)
- [Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement](https://mlsanity.com/paper/2608.23098/) (2026)
- [Which Forms of Caregiver Feedback Support Grammar Learning? A Reinforcement-Learning Study of Child-Like Language Models](https://mlsanity.com/paper/2609.08576/) (2026)

## Abstract (arXiv)

Children efficiently acquire language not just by listening, but by interacting with others in their social environment. Conversely, large language models are typically trained with next-word prediction on massive amounts of text. Motivated by this contrast, we investigate whether language models can be trained with less data by learning not only from next-word prediction but also from high-level, cognitively inspired feedback. We train a student model to generate stories, which a teacher model rates on readability, narrative coherence, and creativity. By varying the amount of pretraining before the feedback loop, we assess the impact of this interactive learning on formal and functional linguistic competence. We find that the high-level feedback is highly data efficient: With just 1 M words of input in interactive learning, storytelling skills can improve as much as with 410 M words of next-word prediction.