On the Challenges of Using Large Language Models for NCL Code Generation

Abstract

A significant concern raised in the domain of authoring tools for interactive Digital TV (iDTV) has been their usability when considering the target audience, which typically consists of content creators and not necessarily programmers. NCL (Nested Context Language), the declarative language for developing interactive applications for Brazilian Digital TV and an ITU-T Recommendation for IPTV services, is a simple declarative language but not an easy tool for non-technical authors. The proliferation of Large Language Models (LLMs) has recently instigated substantial transformations across several domains, including synthesizing code with remarkable potential. This paper proposes an investigation into the challenges of using LLMs to aid automatic NCL code generation/synthesis in authoring tools for iDTV content production. It shows initial evidence that current pre-trained LLMs cannot synthesize NCL code with satisfactory quality. In this context, we raise the main challenges for NCL code generation using LLMs and some issues related to the good practices for engineering prompts and integrating pre-trained LLMs into multimedia authoring tools.