LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional capability, and an inability to maintain a consistent character. Knowledge graphs are commonly used forms of external knowledge and may provide solutions to these challenges. This paper introduces three proposals, utilizing knowledge graphs to enhance LLM generation. Firstly, dynamic knowledge graph embeddings and recommendation could allow for the integration of new information and the selection of relevant knowledge for response generation. Secondly, storing entities with emotional values as additional features may provide knowledge that is better emotionally aligned with the user input. Thirdly, integrating character information through narrative bubbles would maintain character consistency, as well as introducing a structure that would readily incorporate new information.

Most organizations are well aware of what economists are calling the Fourth Industrial Revolution1 and what it could mean for the future of work.2 Up to an estimated 47 percent of US jobs face potential automation over the next 20 years, driven primarily by rapid advances in AI, cognitive computing, and automation of repetitive, rule-based tasks.3 Other disruptive forces seem to be shaping the future of work as well--many organizations are shifting to more team-based structures; workplaces are increasingly virtual, flexible, and geographically agnostic; the overall workforce is becoming more diverse, multigenerational, and dispersed; and most careers are morphing from following predictable road maps to constant reinvention. In the face of this, various leaders across industries are reimagining their workforce models to explore how they can use technology, expanded work settings, and alternative talent to address these disruptive forces. In addition, many are reevaluating their talent profiles, including how they measure the skill sets required for success in the future.

To be productive in the age of automation, human skills as well as social and emotional capabilities will matter more than anything. The future of work in a world of robots may not be as bleak for us humans after all, with a range of our skills pivotal for managing data and automation. 'Deep end-market intimacy will become the space of most demand, not the technology itself' – ROB CURLEY According to Curley, the pace at which technology changes has always led to skills gaps as organisations and staff attempt to keep up. This, he says, is not a new issue but there is currently more impacting change than simply the advances in technology that are taking place. "Because organisations do not have enough skills internally to do the jobs, we are seeing more and more companies coming together with universities, innovation centres and product vendors, facilitated by smaller specialist companies, to bring the technology process capability in-house. But there are still skillset gaps," said Curley.