Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction
This work addresses argument quality prediction for natural language processing applications, but it is incremental as it builds on existing shared task frameworks and methods.
The authors tackled argument quality prediction by combining multiple training paradigms and prompting with GPT-3, finding that a mixed prediction setup outperformed single models, with GPT-3 prompting achieving the best results for argument validity and a model using all three paradigms performing best for argument novelty.
This paper describes our contributions to the Shared Task of the 9th Workshop on Argument Mining (2022). Our approach uses Large Language Models for the task of Argument Quality Prediction. We perform prompt engineering using GPT-3, and also investigate the training paradigms multi-task learning, contrastive learning, and intermediate-task training. We find that a mixed prediction setup outperforms single models. Prompting GPT-3 works best for predicting argument validity, and argument novelty is best estimated by a model trained using all three training paradigms.