Human-AI Interactions Through A Gricean Lens

@article{Panfili2021HumanAIIT,
  title={Human-AI Interactions Through A Gricean Lens},
  author={Laura Panfili and Steve Duman and Andrew Nave and Kate Ridgeway and Nathan Eversole and R. Sarikaya},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.09140}
}
Grice’s Cooperative Principle (1975), which describes the implicit maxims that guide effective conversation, has long been applied to conversations between humans. However, as humans begin to interact with non-human dialogue systems more frequently and in a broader scope, an important question emerges: what principles govern those interactions? In the present study, this question is addressed, as human-AI interactions are categorized using Grice’s four maxims. In doing so, it demonstrates the… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 13 REFERENCES
Single or Multiple Conversational Agents?: An Interactional Coherence Comparison
TLDR
It is found that implementing a meta-chatbot may not be necessary, since similar conversation structures occur when interacting to multiple chatbots, but different interactional aspects must be considered for each scenario. Expand
Interaction Quality: Assessing the quality of ongoing spoken dialog interaction by experts - And how it relates to user satisfaction
TLDR
This study presents a novel expert-based approach to assess the quality of ongoing Spoken Dialog System (SDS) interactions and concludes that this paradigm could render SDSs more user friendly and improve user acceptance. Expand
A new friend in our smartphone?: observing interactions with chatbots in the search of emotional engagement
TLDR
The personal psychological background of participants was found critical while the experience itself allowed them to imagine new possible relations with chatbots, and some insights are shown on how people understand and empathize with future interactions with conversational agents and other non-visual interfaces. Expand
Logic and Conversation
As Grice’s enthusiasm for ordinary language philosophy became increasingly qualified during the 1950s, his interest was growing in the rather different styles of philosophy of language then currentExpand
What Can You Do?: Studying Social-Agent Orientation and Agent Proactive Interactions with an Agent for Employees
TLDR
A 17-day field study of a prototype of a personal AI agent that helps employees find work-related information is conducted and it is found that user differences in social-agent orientation and aversion to agent proactive interactions can be inferred from behavioral signals. Expand
"Alexa is my new BFF": Social Roles, User Satisfaction, and Personification of the Amazon Echo
TLDR
Results indicate marked variance in how people refer to the device, with over half using the personified name Alexa but most referencing the device with object pronouns, and personification predicts user satisfaction with the Echo. Expand
On relevance again: From philosophy of language across ‘pragmatics and power’ to global relevance☆
This paper, largely motivated by Harris (1995), revisits the issue of the Cooperative Principle and, in particular, relevance. I would, firstly, like to note that even before the emergence ofExpand
Pragmatics and power
Abstract This paper sets out to ascertain on the basis of actual language behaviour whether ‘universal pragmatics’, especially Grice's maxims and Habermas's validity claims, can provide a sustainableExpand
Survey on evaluation methods for dialogue systems
TLDR
This paper distinguishes between the various classes of dialogue systems (task-oriented, conversational, and question-answering dialogue systems) by introducing the main technologies developed for the dialogue systems and then presenting the evaluation methods regarding that class. Expand
PsychoPy2: Experiments in behavior made easy
TLDR
The most notable addition has been that Builder interface, allowing users to create studies with minimal or no programming, while also allowing the insertion of Python code for maximal flexibility. Expand
...
1
2
...