Toward Stance-based Personas for Opinionated Dialogues
This work addresses the need for more nuanced personality modeling in AI dialogue systems, though it appears incremental by extending fact-based personas to include stances.
The authors tackled the problem of superficial persona representations in dialogue systems by proposing stance-based personas to capture opinions, values, and beliefs, showing that these representations can grasp abstract aspects of author persona in claim generation.
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations. Still, the representation of such personas has thus far been limited to a fact-based representation (e.g. "I have two cats."). We argue that these representations remain superficial w.r.t. the complexity of human personality. In this work, we propose to make a step forward and investigate stance-based persona, trying to grasp more profound characteristics, such as opinions, values, and beliefs to drive language generation. To this end, we introduce a novel dataset allowing to explore different stance-based persona representations and their impact on claim generation, showing that they are able to grasp abstract and profound aspects of the author persona.