Recent studies show that traditional fairytales are rife with harmful gender biases. To help mitigate these gender biases in fairytales, this work aims to assess learned biases of language models by evaluating their robustness against gender perturbations. Specifically, we focus on Question Answering (QA) tasks in fairytales. Using counterfactual data augmentation to the FairytaleQA dataset, we evaluate model robustness against swapped gender character information, and then mitigate learned biases by introducing counterfactual gender stereotypes during training time. We additionally introduce a novel approach that utilizes the massive vocabulary of language models to support text genres beyond fairytales. Our experimental results suggest that models are sensitive to gender perturbations, with significant performance drops compared to the original testing set. However, when first fine-tuned on a counterfactual training dataset, models are less sensitive to the later introduced anti-gender stereotyped text.

The quality of text-to-image generation is continuously improving, yet the boundaries of its applicability are still unclear. In particular, refinement of the text input with the objective of achieving better results - commonly called prompt engineering - so far seems to have not been geared towards work with pre-existing texts. We investigate whether text-to-image generation and prompt engineering could be used to generate basic illustrations of popular fairytales. Using Midjourney v4, we engage in action research with a dual aim: to attempt to generate 5 believable illustrations for each of 5 popular fairytales, and to define a prompt engineering process that starts from a pre-existing text and arrives at an illustration of it. We arrive at a tentative 4-stage process: i) initial prompt, ii) composition adjustment, iii) style refinement, and iv) variation selection. We also discuss three reasons why the generation model struggles with certain illustrations: difficulties with counts, bias from stereotypical configurations and inability to depict overly fantastic situations. Our findings are not limited to the specific generation model and are intended to be generalisable to future ones.

A young girl once enjoyed reading fairytales. Every night before bed, she would read them with her mother. However, as she grew older, she realized that the stories didn't always make sense. They were extremely predictable, and the personalities didn't alter much. "We could do better than this," she thought to herself.

World building forms the foundation of any task that requires narrative intelligence. In this work, we focus on procedurally generating interactive fiction worlds--text-based worlds that players "see" and "talk to" using natural language. Generating these worlds requires referencing everyday and thematic commonsense priors in addition to being semantically consistent, interesting, and coherent throughout. Using existing story plots as inspiration, we present a method that first extracts a partial knowledge graph encoding basic information regarding world structure such as locations and objects. This knowledge graph is then automatically completed utilizing thematic knowledge and used to guide a neural language generation model that fleshes out the rest of the world.We perform human participant-based evaluations, testing our neural model's ability to extract and fill-in a knowledge graph and to generate language conditioned on it against rule-based and human-made baselines. Our code is available at https://github.com/

The Brothers Grimm have been dead more than 150 years, but they recently released a new story with a little help from artificial intelligence. The Princess and the Fox was created after a group of writers, artists and developers used a programme inspired by predictive text on phones to scan the collected stories of the Brothers Grimm to suggest words and similar phrases. Human writers then took over, to help shape the AI's algorithmic suggestions into the latest Grimm fairytale. The new tale tells the story of a talking fox who helps a lowly miller's son rescue a beautiful princess from the fate of having to marry a horrible prince she does not love. But here's the thing, the Brothers Grimm didn't actually write their fairytales in the first place.

The Grimm brothers' seminal book of fairytales is over two centuries old. But the duo has been credit with a new story, "The Princess and the Fox," just this month--with some help from artificial intelligence. Released by the meditation app Calm, "The Princess and the Fox" was written by Botnik, a company that uses machine learning and predictive algorithms to write text. The story was released on the app on April 11, and is available in audio form. This is not necessarily new: AI-generated fairytales have been around for a long while now, with the first dating all the way back to the 1930s, as Mark Riedl, a professor of artificial intelligence at Georgia Tech, writes in his history of AI-generated stories. And programs that mimic the Grimm brothers' language have also been done before, according to Isaac Karth, an AI researcher at the University of California, Santa Cruz.

It was recently reported that the meditation app Calm had published a "new" fairytale by the Brothers Grimm. However, The Princess and the Fox was written not by the brothers, who died over 150 years ago, but by humans using an artificial intelligence (AI) tool. It's the first fairy tale written by an AI, claims Calm, and is the result of a collaboration with Botnik Studios - a community of writers, artists and developers. Calm says the technique could be referred to as "literary cloning". Botnik employees used a predictive-text program to generate words and phrases that might be found in the original Grimm fairytales.

Note: To comply with the blind reviewing guidelines, the name of the system in this paper has been changed to SWNN (system with no name) and the name of the language employed by the system to LWNN (language with no name). We are swimming in a sea of stories, coming from printed, audio and visual media as well as delivered by live speech. Even more important is the narrative of our own lives, which includes events which we witness, but also stories we plan, infer, imagine or daydream. Agents interacting with humans will need to become adept on manipulating stories. This includes creating stories from their life experience, recalling or re-narrating stories with various levels of accuracy, predicting future events in stories, expressing surprise and so on.