A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
This work addresses evaluation challenges in DST for NLP researchers, offering a zero-shot method that reduces reliance on labeled data and improves semantic consistency, though it is incremental as it builds on existing LLM-based evaluation approaches.
The paper tackles the problem of evaluating dialogue state tracking (DST) by proposing a two-dimensional zero-shot evaluation method using GPT-4, which divides evaluation into accuracy and completeness dimensions and includes manual reasoning paths in prompting, achieving better performance compared to baselines and consistency with traditional exact matching methods.
Dialogue state tracking (DST) is evaluated by exact matching methods, which rely on large amounts of labeled data and ignore semantic consistency, leading to over-evaluation. Currently, leveraging large language models (LLM) in evaluating natural language processing tasks has achieved promising results. However, using LLM for DST evaluation is still under explored. In this paper, we propose a two-dimensional zero-shot evaluation method for DST using GPT-4, which divides the evaluation into two dimensions: accuracy and completeness. Furthermore, we also design two manual reasoning paths in prompting to further improve the accuracy of evaluation. Experimental results show that our method achieves better performance compared to the baselines, and is consistent with traditional exact matching based methods.