On the Automatic Generation and Simplification of Children's Stories

• URL: http://arxiv.org/abs/2310.18502v1
• Date: Fri, 27 Oct 2023 21:31:34 GMT
• Title: On the Automatic Generation and Simplification of Children's Stories
• Authors: Maria Valentini, Jennifer Weber, Jesus Salcido, T\'ea Wright, Eliana Colunga, Katharina Kann
• Abstract summary: We first examine the ability of several popular large language models to generate stories with properly adjusted lexical and readability levels. As a second experiment, we explore the ability of state-of-the-art lexical simplification models to generalize to the domain of children's stories. We find that, while the strongest-performing current lexical simplification models do not perform as well on material designed for children due to their reliance on large language models behind the scenes.
• Score: 14.465545222216749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With recent advances in large language models (LLMs), the concept of automatically generating children's educational materials has become increasingly realistic. Working toward the goal of age-appropriate simplicity in generated educational texts, we first examine the ability of several popular LLMs to generate stories with properly adjusted lexical and readability levels. We find that, in spite of the growing capabilities of LLMs, they do not yet possess the ability to limit their vocabulary to levels appropriate for younger age groups. As a second experiment, we explore the ability of state-of-the-art lexical simplification models to generalize to the domain of children's stories and, thus, create an efficient pipeline for their automatic generation. In order to test these models, we develop a dataset of child-directed lexical simplification instances, with examples taken from the LLM-generated stories in our first experiment. We find that, while the strongest-performing current lexical simplification models do not perform as well on material designed for children due to their reliance on large language models behind the scenes, some models that still achieve fairly strong results on general data can mimic or even improve their performance on children-directed data with proper fine-tuning, which we conduct using our newly created child-directed simplification dataset.

Related papers

• Scalable Early Childhood Reading Performance Prediction [5.413138072912236]
  There are no suitable publicly available educational datasets for modeling and predicting future reading performance. In this work, we introduce the Enhanced Core Reading Instruction ECRI dataset. We leverage the dataset to empirically evaluate the ability of state-of-the-art machine learning models to recognize early childhood educational patterns.
  arXiv  Detail & Related papers  (2024-12-05T18:59:50Z)
• KidLM: Advancing Language Models for Children -- Early Insights and Future Directions [7.839083566878183]
  We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. We propose a new training objective, Stratified Masking, which dynamically adjusts masking probabilities based on our domain-specific child language data. Experimental evaluations demonstrate that our model excels in understanding lower grade-level text, maintains safety by avoiding stereotypes, and captures children's unique preferences.
  arXiv  Detail & Related papers  (2024-10-04T19:35:44Z)
• Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas [7.585433383340306]
  We show that tokenization-free, phoneme- and grapheme-based language models can achieve strong linguistic performance. Our findings suggest a promising direction for creating more linguistically plausible language models.
  arXiv  Detail & Related papers  (2024-10-02T12:36:08Z)
• Evolving Knowledge Distillation with Large Language Models and Active Learning [46.85430680828938]
  Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks. Previous research has attempted to distill the knowledge of LLMs into smaller models by generating annotated data. We propose EvoKD: Evolving Knowledge Distillation, which leverages the concept of active learning to interactively enhance the process of data generation using large language models.
  arXiv  Detail & Related papers  (2024-03-11T03:55:24Z)
• Continual Learning for Large Language Models: A Survey [95.79977915131145]
  Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. This paper surveys recent works on continual learning for LLMs.
  arXiv  Detail & Related papers  (2024-02-02T12:34:09Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [57.74233319453229]
  Large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task. We propose MultiCSR, a multi-level contrastive sentence representation learning framework that decomposes the process of prompting LLMs to generate a corpus. Our experiments reveal that MultiCSR enables a less advanced LLM to surpass the performance of ChatGPT, while applying it to ChatGPT achieves better state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-17T03:21:43Z)
• Trustworthiness of Children Stories Generated by Large Language Models [0.0]
  We evaluate the trustworthiness of children's stories generated by Large Language Models. Our findings suggest that LLMs still struggle to generate children's stories at the level of quality and nuance found in actual stories.
  arXiv  Detail & Related papers  (2023-07-25T22:55:51Z)
• Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning [104.58874584354787]
  In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
  arXiv  Detail & Related papers  (2023-01-27T18:59:01Z)
• The Next Chapter: A Study of Large Language Models in Storytelling [51.338324023617034]
  The application of prompt-based learning with large language models (LLMs) has exhibited remarkable performance in diverse natural language processing (NLP) tasks. This paper conducts a comprehensive investigation, utilizing both automatic and human evaluation, to compare the story generation capacity of LLMs with recent models. The results demonstrate that LLMs generate stories of significantly higher quality compared to other story generation models.
  arXiv  Detail & Related papers  (2023-01-24T02:44:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.