Prompting for a conversation: How to control a dialog model?
This addresses the problem of dull and limited responses in dialog agents for conversational AI applications, offering an incremental improvement over fine-tuning methods.
The paper tackles the trade-off in dialog modeling between using large pre-trained models for diversity and fine-tuning for controlled responses, finding that prompting conditioned on queries improves BLEU scores and enhances response diversity and novelty compared to fine-tuning.
Dialog modelling faces a difficult trade-off. Models are trained on a large amount of text, yet their responses need to be limited to a desired scope and style of a dialog agent. Because the datasets used to achieve the former contain language that is not compatible with the latter, pre-trained dialog models are fine-tuned on smaller curated datasets. However, the fine-tuning process robs them of the ability to produce diverse responses, eventually reducing them to dull conversation partners. In this paper we investigate if prompting can mitigate the above trade-off. Specifically, we experiment with conditioning the prompt on the query, rather than training a single prompt for all queries. By following the intuition that freezing the pre-trained language model will conserve its expressivity, we find that compared to fine-tuning, prompting can achieve a higher BLEU score and substantially improve the diversity and novelty of the responses.