Trustworthiness of Children Stories Generated by Large Language Models
Prabin Bhandari, Hannah Marie Brennan
TL;DR
This paper evaluates the trustworthiness of children's stories generated by large language models, highlighting their current limitations in quality and nuance compared to real stories.
Contribution
It provides a systematic assessment of LLM-generated children's stories and compares them with authentic stories to identify gaps in quality and trustworthiness.
Findings
LLMs struggle to match the quality of real children's stories
Generated stories lack the nuance found in authentic stories
Assessment measures reveal significant gaps in trustworthiness
Abstract
Large Language Models (LLMs) have shown a tremendous capacity for generating literary text. However, their effectiveness in generating children's stories has yet to be thoroughly examined. In this study, we evaluate the trustworthiness of children's stories generated by LLMs using various measures, and we compare and contrast our results with both old and new children's stories to better assess their significance. Our findings suggest that LLMs still struggle to generate children's stories at the level of quality and nuance found in actual stories
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Computational and Text Analysis Methods