We present online learning of Hierarchical Task Network (HTN) methods in the context of integrated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose tasks into subtasks. Our method learner is built on top of the ChatHTN planner. ChatHTN queries ChatGPT to generate a decomposition of a task into primitive tasks when no applicable method for the task is available. In this work, we extend ChatHTN. Namely, when ChatGPT generates a task decomposition, ChatHTN learns from it, akin to memoization. However, unlike memoization, it learns a generalized method that applies not only to the specific instance encountered, but to other instances of the same task.. We conduct experiments on two domains and demonstrate that our online learning procedure reduces the number of calls to ChatGPT while solving at least as many problems, and in some cases, even more.

When the Nigerian government announced plans in April to develop a multilingual artificial intelligence tool to boost digital inclusion across the West African nation, 28-year-old computer science student Lwasinam Lenham Dilli was thrilled. Dilli had struggled to scrape datasets from the internet to build a large language model (LLM), used to power AI chatbots, in his native Hausa language as part of his final-year project at university. "I needed texts in English and their corresponding translation in Hausa, but I couldn't get anything online; (there was) no clean data," Dilli said.

Safeguards designed to prevent OpenAI's GPT-4 artificial intelligence from answering harmful prompts failed when it received requests in languages such as Scots Gaelic or Zulu. This allowed researchers to get AI-generated answers on how to build a homemade bomb or perform insider trading. The vulnerability demonstrated in the large language model involves instructing the AI in languages that are mostly absent from its training data.