PICKD: In-Situ Prompt Tuning for Knowledge-Grounded Dialogue Generation

Generating informative, coherent and fluent responses to user queries is challenging yet critical for a rich user experience and the eventual success of dialogue systems. Knowledge-grounded dialogue systems leverage external knowledge to induce relevant facts in a dialogue. These systems need to understand the semantic relatedness between the dialogue context and the available knowledge, thereby utilising this information for response generation. Although various innovative models have been proposed, they neither utilise the semantic entailment between the dialogue history and the knowledge nor effectively process knowledge from both structured and unstructured sources. In this work, we propose PICKD, a two-stage framework for knowledgeable dialogue. The first stage involves the Knowledge Selector choosing knowledge pertinent to the dialogue context from both structured and unstructured knowledge sources. PICKD leverages novel In-Situ prompt tuning for knowledge selection, wherein prompt tokens are injected into the dialogue-knowledge text tokens during knowledge retrieval. The second stage employs the Response Generator for generating fluent and factual responses by utilising the retrieved knowledge and the dialogue context. Extensive experiments on three domain-specific datasets exhibit the effectiveness of PICKD over other baseline methodologies for knowledge-grounded dialogue. The source is available at https://github.com/rajbsk/pickd.