Diving Deep into Modes of Fact Hallucinations in Dialogue Systems
This work addresses fact hallucination in chatbots, which hinders conversation flow, but it is incremental as it focuses on dataset creation and baseline models rather than a novel solution.
The paper tackled fact hallucination in knowledge-grounded dialogue systems by identifying hallucination modes through human feedback and creating a synthetic dataset (FADE) for detection, with baseline models evaluated against human-verified data and benchmarks.
Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. Frequently entities with no references in knowledge sources and conversation history are introduced into responses, thus hindering the flow of the conversation -- existing work attempt to overcome this issue by tweaking the training procedure or using a multi-step refining method. However, minimal effort is put into constructing an entity-level hallucination detection system, which would provide fine-grained signals that control fallacious content while generating responses. As a first step to address this issue, we dive deep to identify various modes of hallucination in KG-grounded chatbots through human feedback analysis. Secondly, we propose a series of perturbation strategies to create a synthetic dataset named FADE (FActual Dialogue Hallucination DEtection Dataset). Finally, we conduct comprehensive data analyses and create multiple baseline models for hallucination detection to compare against human-verified data and already established benchmarks.