Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs
This addresses the challenge of open-domain dialogues and noisy inputs in task-oriented dialogue systems, offering a more flexible and interpretable solution.
This paper tackles the problem of dialogue state tracking by introducing a novel approach that uses large language models to generate natural language descriptions of dialogue states instead of traditional slot-value representations. The method significantly outperforms existing baselines on MultiWOZ 2.1 and Taskmaster-1 datasets in Joint Goal Accuracy and Slot Accuracy.
This paper introduces a novel approach to Dialogue State Tracking (DST) that leverages Large Language Models (LLMs) to generate natural language descriptions of dialogue states, moving beyond traditional slot-value representations. Conventional DST methods struggle with open-domain dialogues and noisy inputs. Motivated by the generative capabilities of LLMs, our Natural Language DST (NL-DST) framework trains an LLM to directly synthesize human-readable state descriptions. We demonstrate through extensive experiments on MultiWOZ 2.1 and Taskmaster-1 datasets that NL-DST significantly outperforms rule-based and discriminative BERT-based DST baselines, as well as generative slot-filling GPT-2 DST models, in both Joint Goal Accuracy and Slot Accuracy. Ablation studies and human evaluations further validate the effectiveness of natural language state generation, highlighting its robustness to noise and enhanced interpretability. Our findings suggest that NL-DST offers a more flexible, accurate, and human-understandable approach to dialogue state tracking, paving the way for more robust and adaptable task-oriented dialogue systems.