# Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs

arXiv: https://arxiv.org/abs/2503.08857 · HTML: https://mlsanity.com/paper/2503.08857/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning](https://mlsanity.com/paper/2401.06805/) (2024)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024)
- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [Large Language Models as Zero-shot Dialogue State Tracker through Function Calling](https://mlsanity.com/paper/2402.10466/) (2024)
- [Closing the Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/2310.01693/) (2023)
- [Fine-Grained Distillation for Long Document Retrieval](https://mlsanity.com/paper/2212.10423/) (2022)
- [The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs](https://mlsanity.com/paper/2303.12961/) (2023)
- [Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation](https://mlsanity.com/paper/2405.13037/) (2024)
- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [Robust Dialogue State Tracking with Weak Supervision and Sparse Data](https://mlsanity.com/paper/2202.03354/) (2022)
- [Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates](https://mlsanity.com/paper/2407.08100/) (2024)
- [DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning](https://mlsanity.com/paper/2212.02851/) (2022)
- [S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs](https://mlsanity.com/paper/2309.08827/) (2023)
- [Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2310.10520/) (2023)
- [A survey of textual cyber abuse detection using cutting-edge language models and large language models](https://mlsanity.com/paper/2501.05443/) (2025)

## Built on by (most cited first, 3 of 3)

- [Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents](https://mlsanity.com/paper/2602.16246/) (2026)
- [Multimodal Hidden Markov Models for Persistent Emotional State Tracking](https://mlsanity.com/paper/2605.12838/) (2026)
- [An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration](https://mlsanity.com/paper/2609.07152/) (2026)

## Abstract (arXiv)

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.