Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs
This work addresses the problem of enabling conversational question answering over knowledge graphs for users needing interactive information retrieval, but it is incremental as it applies existing methods to a new task.
The paper evaluated large language models' ability to generate graph queries from dialogues for knowledge-based conversational question answering, finding that few-shot prompting and fine-tuning significantly improved performance, especially for smaller models with lower zero-shot capabilities.
Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance.