Viola: A Topic Agnostic Generate-and-Rank Dialogue System

TL;DR

Viola is a topic-agnostic, generate-and-rank dialogue system leveraging large language models, knowledge graphs, and safety mechanisms to produce contextually relevant and safe open-domain spoken conversations.

Contribution

It introduces Viola, a novel dialogue system combining neural, template-based, and knowledge-grounded responses with a fine-tuned ranker and safety filters, advancing open-domain conversational AI.

Findings

Viola participated in Alexa Prize Socialbot Challenge 4.

The system effectively integrates diverse response sources.

Analysis highlights strengths and areas for improvement.

Abstract

We present Viola, an open-domain dialogue system for spoken conversation that uses a topic-agnostic dialogue manager based on a simple generate-and-rank approach. Leveraging recent advances of generative dialogue systems powered by large language models, Viola fetches a batch of response candidates from various neural dialogue models trained with different datasets and knowledge-grounding inputs. Additional responses originating from template-based generators are also considered, depending on the user's input and detected entities. The hand-crafted generators build on a dynamic knowledge graph injected with rich content that is crawled from the web and automatically processed on a daily basis. Viola's response ranker is a fine-tuned polyencoder that chooses the best response given the dialogue history. While dedicated annotations for the polyencoder alone can indirectly steer it away from choosing problematic responses, we add rule-based safety nets to detect neural degeneration and a dedicated classifier to filter out offensive content. We analyze conversations that Viola took part in for the Alexa Prize Socialbot Grand Challenge 4 and discuss the strengths and weaknesses of our approach. Lastly, we suggest future work with a focus on curating conversation data specifcially for socialbots that will contribute towards a more robust data-driven socialbot.