An official website of the United States government
Effective storytelling relies on engagement and interaction. This work develops an automated software platform for telling stories to children and investigates the impact of two design choices on children’s engagement and willingness to interact with the system: story distribution and the use of complex gesture. A storyteller condition compares stories told in a third person, narrator voice with those distributed between a narrator and first-person story characters. Basic gestures are used in all our storytellings, but, in a second factor, some are augmented with gestures that indicate conversational turn changes, references to other characters and prompt children to ask questions. An analysis of eye gaze indicates that children attend more to the story when a distributed storytelling model is used. Gesture prompts appear to encourage children to ask questions, something that children did, but at a relatively low rate. Interestingly, the children most frequently asked “why” questions. Gaze switching happened more quickly when the story characters began to speak than for narrator turns. These results have implications for future agent-based storytelling system research.
more »
« less
Gender and Representation Bias in GPT-3 Generated Stories
Using topic modeling and lexicon-based word similarity, we find that stories generated by GPT-3 exhibit many known gender stereotypes. Generated stories depict different topics and descriptions depending on GPT-3’s perceived gender of the character in a prompt, with feminine characters more likely to be associated with family and appearance, and described as less powerful than masculine characters, even when associated with high power verbs in a prompt. Our study raises questions on how one can avoid unintended social biases when using large language models for storytelling.
more »
« less
- Award ID(s):
- 1942591
- PAR ID:
- 10237395
- Date Published:
- Journal Name:
- Proceedings of the Third Workshop on Narrative Understanding
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Effective storytelling relies on engagement and interaction. This work develops an automated software platform for telling stories to children and investigates the impact of two design choices on children’s engagement and willingness to interact with the system: story distribution and the use of complex gesture. A storyteller condition compares stories told in a third person, narrator voice with those distributed between a narrator and first-person story characters. Basic gestures are used in all our storytellings, but, in a second factor, some are augmented with gestures that indicate conversational turn changes, references to other characters and prompt children to ask questions. An analysis of eye gaze indicates that children attend more to the story when a distributed storytelling model is used. Gesture prompts appear to encourage children to ask questions, something that children did, but at a relatively low rate. Interestingly, the children most frequently asked “why” questions. Gaze switching happened more quickly when the story characters began to speak than for narrator turns. These results have implications for future agent-based storytelling system research.more » « less
-
In this paper, we study a controllable prompt adversarial attacking problem for text guided image generation (Text2Image) models in the black-box scenario, where the goal is to attack specific visual subjects (e.g., changing a brown dog to white) in a generated image by slightly, if not imperceptibly, perturbing the characters of the driven prompt (e.g., “brown” to “br0wn”). Our study is motivated by the limitations of current Text2Image attacking approaches that still rely on manual trials to create adversarial prompts. To address such limitations, we develop CharGrad, a character-level gradient based attacking framework that replaces specific characters of a prompt with pixel-level similar ones by interactively learning the perturbation direction for the prompt and updating the attacking examiner for the generated image based on a novel proxy perturbation representation for characters. We evaluate CharGrad using the texts from two public image captioning datasets. Results demonstrate that CharGrad outperforms existing text adversarial attacking approaches on attacking various subjects of generated images by black-box Text2Image models in a more effective and efficient way with less perturbation on the characters of the prompts.more » « less
-
Language models that can learn a task at inference time, called in-context learning (ICL), show increasing promise in natural language inference tasks. In ICL, a model user constructs a prompt to describe a task with a natural language instruction and zero or more examples, called demonstrations. The prompt is then input to the language model to generate a completion. In this paper, we apply ICL to the design and evaluation of satisfaction arguments, which describe how a requirement is satisfied by a system specification and associated domain knowledge. The approach builds on three prompt design patterns, including augmented generation, prompt tuning, and chain-of-thought prompting, and is evaluated on a privacy problem to check whether a mobile app scenario and associated design description satisfies eight consent requirements from the EU General Data Protection Regulation (GDPR). The overall results show that GPT-4 can be used to verify requirements satisfaction with 96.7% accuracy and dissatisfaction with 93.2% accuracy. Inverting the requirement improves verification of dissatisfaction to 97.2%. Chain-of-thought prompting improves overall GPT-3.5 performance by 9.0% accuracy. We discuss the trade-offs among templates, models and prompt strategies and provide a detailed analysis of the generated specifications to inform how the approach can be applied in practice.more » « less
-
Language-based text provide valuable insights into people’s lived experiences. While traditional qualitative analysis is used to capture these nuances, new paradigms are needed to scale qualitative research effectively. Artificial intelligence presents an unprecedented opportunity to expand the sale of analysis for obtaining such nuances. The study tests the application of GPT-4—a large language modeling—in qualitative data analysis using an existing set of text data derived from 60 qualitative interviews. Specifically, the study provides a practical guide for social and behavioral researchers, illustrating core elements and key processes, demonstrating its reliability by comparing GPT-generated codes with researchers’ codes, and evaluating its capacity for theory-driven qualitative analysis. The study followed a three-step approach: (1) prompt engineering, (2) reliability assessment by comparison of GPT-generated codes with researchers’ codes, and (3) evaluation of theory-driven thematic analysis on psychological constructs. The study underscores the utility of GPT’s capabilities in coding and analyzing text data with established qualitative methods while highlighting the need for qualitative expertise to guide GPT applications. Recommendations for further exploration are also discussed.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
