Author(s): Marie Stephen Leo Originally published on Towards AI. Comparing SetFit, FastFit, and Semantic Router to find the best NLP chatbot intent detection algorithmImage generated by Author using ChatGPT In the pre-ChatGPT era, chatbot frameworks like Dialogflow and Rasa used intent detection to respond only to topics that the developers explicitly programmed, ensuring they would stick closely to their intended use and prevent prompt injections. OpenAI’s ChatGPT changed that with its incredible reasoning abilities, which allowed a Large Language Model (LLM) to decide how to answer users’ questions on various topics without explicitly programming a flow for handling each topic. You just “prompt” the LLM on which topics to respond to and which to decline and let the LLM decide. However, numerous examples in the post-ChatGPT era have repeatedly shown how finicky a pure “prompt” based approach is. In my journey working with LLMs over the past year+, one of the most reliable methods I’ve found to restrict LLMs to a desired domain is to follow a 2-step approach that I’ve previously written about on Linkedin and reproducing below. This article was written entirely by a human with help from Grammarly’s grammar checker, which has been my writing method since 2019. Preprocessing guardrail: An LLM call and heuristical rules to decide if the user’s input is from an allowed topic.LLM call: The chatbot logic, such as… Read the full blog for free on Medium. Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor. Published via Towards AI
↧