Explaining Large Language Model-Based Neural Semantic Parsers (Student Abstract)
This work addresses the need for better interpretability in LLM-based semantic parsers, but it is incremental as it focuses on qualitative analysis without introducing new methods or benchmarks.
The authors tackled the problem of understanding the mechanisms behind large language models' success in semantic parsing by studying different explanation methods and qualitatively discussing model behaviors, with the goal of inspiring future research.
While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different methods for explaining an LLM-based semantic parser and qualitatively discusses the explained model behaviors, hoping to inspire future research toward better understanding them.