Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs

TL;DR

This paper explores how large language models can improve dialogue systems by using knowledge graphs to bridge information gaps and enhance understanding in domain-specific conversations.

Contribution

It introduces BridgeKG, a new dialogue corpus, and evaluates large language models' ability to classify grounding acts and identify information in knowledge graphs.

Findings

Models effectively use in-context learning for grounding tasks

Identification of common prediction errors in model outputs

Insights into handling knowledge graphs as semantic layers

Abstract

Knowledge models are fundamental to dialogue systems for enabling conversational interactions, which require handling domain-specific knowledge. Ensuring effective communication in information-providing conversations entails aligning user understanding with the knowledge available to the system. However, dialogue systems often face challenges arising from semantic inconsistencies in how information is expressed in natural language compared to how it is represented within the system's internal knowledge. To address this problem, we study the potential of large language models for conversational grounding, a mechanism to bridge information gaps by establishing shared knowledge between dialogue participants. Our approach involves annotating human conversations across five knowledge domains to create a new dialogue corpus called BridgeKG. Through a series of experiments on this dataset, we empirically evaluate the capabilities of large language models in classifying grounding acts and identifying grounded information items within a knowledge graph structure. Our findings offer insights into how these models use in-context learning for conversational grounding tasks and common prediction errors, which we illustrate with examples from challenging dialogues. We discuss how the models handle knowledge graphs as a semantic layer between unstructured dialogue utterances and structured information items.