Theory of Mind (ToM) is the ability to understand and reflect on the mental states of others. Although this capability is crucial for human interaction, testing on Large Language Models (LLMs) reveals that they possess only a rudimentary understanding of it. Although the most capable closed-source LLMs have come close to human performance on some ToM tasks, they still perform poorly on complex variations of the task that involve more structured reasoning. In this work, we utilize the concept of “pretend-play”, or “Simulation Theory” from cognitive psychology to propose “Decompose-ToM”: an LLM-based inference algorithm that improves model performance on complex ToM tasks. We recursively simulate user perspectives and decompose the ToM task into a simpler set of tasks: subject identification, question-reframing, world model updation, and knowledge availability. We test the algorithm on higher-order ToM tasks and a task testing for ToM capabilities in a conversational setting, demonstrating that our approach shows significant improvement across models compared to baseline methods while requiring minimal prompt tuning across tasks and no additional model training. Our code is publicly available.

While creativity has been previously studied in Child-Robot Interaction (cHRI), the effect of regulatory focus on creativity skills has not been investigated. This paper presents an exploratory study that, for the first time, uses the Regulatory Focus Theory (RFT) to assess children's creativity skills in an educational context with a social robot. We investigated whether two key emotional regulation techniques, promotion (approach) and prevention (avoidance), stimulate creativity during a story-telling activity between a child and a robot. We conducted a between-subjects field study with 69 children between the ages of 7 and 9 years old, divided between two study conditions: (1) promotion, where a social robot primes children for action by eliciting positive emotional states, and (2) prevention, where a social robot primes children for avoidance by evoking a states related to security and safety associated with blockage-oriented behaviors. To assess changes in creativity as a response to the priming interaction, children were asked to tell stories to the robot before (pre-test) and after (post-test) the priming interaction. We measured creativity levels by analyzing the verbal content of the stories. We coded verbal expressions related to creativity variables, including fluency, flexibility, elaboration, and originality. Our results show that children in the promotion condition generated significantly more ideas, and their ideas were on average more original in the stories they created in the post-test rather than in the pre-test. We also modeled the process of creativity that emerges during storytelling in response to the robot's verbal behavior. This paper enriches the scientific understanding of creativity emergence in child-robot collaborative interactions.

We present the design and evaluation of a storytelling activity between children and an autonomous robot aiming at nurturing children’s creativity. We assessed whether a robot displaying creative behavior will positively impact children’s creativity skills in a storytelling context. We developed two models for the robot to engage in the storytelling activity: creative model, where the robot generates creative story ideas, and the non-creative model, where the robot generates non-creative story ideas. We also investigated whether the type of the storytelling interaction will have an impact on children’s creativity skills. We used two types of interaction: 1) Collaborative, where the child and the robot collaborate together by taking turns to tell a story. 2) Non-collaborative: where the robot first tells a story to the child and then asks the child to tell it another story. We conducted a between-subjects study with 103 children in four different conditions: Creative collaborative, Non-creative collaborative, Creative non-collaborative and Non-Creative non-collaborative. The children’s stories were evaluated according to the four standard creativity variables: fluency, flexibility, elaboration and originality. Results emphasized that children who interacted with a creative robot showed higher creativity during the interaction than children who interacted with a non-creative robot. Nevertheless, no significant effect of the type of the interaction was found on children’s creativity skills. Our findings are significant to the Child-Robot interaction (cHRI) community since they enrich the scientific understanding of the development of child-robot encounters for educational applications.

In an attempt to nurture children's creativity, we developed a creative conversational agent to be used in a collaborative storytelling context with a child. We presented a novel approach to develop creative Artificial Intelligence (AI). Our approach uses the four creativity measures: fluency, flexi-bility, elaboration and originality in order to generate creative behavior. We analyzed and annotated our previously collected storytelling data sets -collected with children- according to our four creativity measures. We then used the extracted and annotated data (636 statements) in order to fine-tune two pre-trained language models (Open AI GPT-3). The two models were aimed at generating creative versus non-creative behavior in a collaborative storytelling scenario. We developed the two models to be able to assess the results and compare them together. We conducted an evaluation to assess stories generated collaboratively between a human and both agents separately (n = 26). Adult Users rated the creativity of the agent according to the stories generated. Results showed that the creative agent was perceived as significantly more creative than the non-creative agent. With the experiment results confirming the validity of our system, we may therefore proceed with testing the effects of the creative behavior of the agent on children's creativity skills.

According to psychology research, emotional induction has positive implications in many domains such as therapy and education. Our aim in this paper was to manipulate the Regulatory Focus Theory to assess its impact on the induction of regulatory focus related emotions in children in a pretend play scenario with a social robot. The Regulatory Focus Theory suggests that people follow one of two paradigms while attempting to achieve a goal; by seeking gains (promotion focus - associated with feelings of happiness) or by avoiding losses (prevention focus - associated with feelings of fear). We conducted a study with 69 school children in two different conditions (promotion vs. prevention). We succeeded in inducing happiness emotions in the promotion condition and found a resulting positive effect of the induction on children’s social engagement with the robot. We also discuss the important implications of these results in both educational and child robot interaction fields.

Creativity is a vital inherent human trait. In an attempt to stimulate children's creativity, we present the design and evaluation of an interaction between a child and a social robot in a storytelling context. Using a software interface, children were asked to collaboratively create a story with the robot. We conducted a study with 38 children in two conditions. In one condition, the children interacted with a robot exhibiting creative behavior while in the other condition, they interacted with a robot exhibiting non creative behavior. The robot's creativity was defined as verbal and performance creativity. The robot's creative and non creative behaviors were extracted from a previously collected data set and were validated in an online survey with 100 participants. Contrary to our initial hypothesis, children's creativity measures were not higher in the creative condition than in the non creative condition. Our results suggest that merely the robot's creative behavior is insufficient to stimulate creativity in children in a child robot interaction. We further discuss other design factors that may facilitate sparking creativity in children in similar settings in the future.

In order to design social agents for long term interactions, it is important to enable them to adapt to the users. In this paper, we chose personality as a medium for adaptation. We conducted a study with 20 participants who watched a story presented by a virtual character in one of two conditions: extroverted or introverted. The study aimed at assessing the impacts of matching the personality of the user with the virtual character through body language on the likability of the character and the information recall of the story. Our findings do not appear to coincide with theoretical expectations since the extroverted character had higher ratings of likability regardless of the personality of the user. Results have also shown a marginal positive effect of the encounter with the introverted character in terms of memory recall. We discuss the important implications that these results may have in the future for human agent interaction design.