Improved Instruction Ordering in Recipe-Grounded Conversation
This work addresses a specific challenge in instructional dialogue for cooking, offering incremental improvements to enhance the reliability of AI assistants in this domain.
The paper tackled the problem of incorrect instruction ordering in recipe-grounded dialogue systems by proposing auxiliary subtasks for user intent detection and instruction state tracking, which improved response generation and revealed that even ChatGPT makes mistakes, with 10.7% of responses containing errors, half of which are out-of-order instructions.
In this paper, we study the task of instructional dialogue and focus on the cooking domain. Analyzing the generated output of the GPT-J model, we reveal that the primary challenge for a recipe-grounded dialog system is how to provide the instructions in the correct order. We hypothesize that this is due to the model's lack of understanding of user intent and inability to track the instruction state (i.e., which step was last instructed). Therefore, we propose to explore two auxiliary subtasks, namely User Intent Detection and Instruction State Tracking, to support Response Generation with improved instruction grounding. Experimenting with our newly collected dataset, ChattyChef, shows that incorporating user intent and instruction state information helps the response generation model mitigate the incorrect order issue. Furthermore, to investigate whether ChatGPT has completely solved this task, we analyze its outputs and find that it also makes mistakes (10.7% of the responses), about half of which are out-of-order instructions. We will release ChattyChef to facilitate further research in this area at: https://github.com/octaviaguo/ChattyChef.