mlsanityData to 14 Oct 2026

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

arXiv 2503.08857 ↗First posted 11 Mar 2025cs.CLcited by 3

Not on the map. Why?

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.

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

21 of 38 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 152
  3. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 140
  4. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  5. 2024Visual In-Context Learning for Large Vision-Language Modelscited by 128
  6. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  7. 2022ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classificationcited by 45
  8. 2024Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Modelscited by 42
  9. 2025Improving Medical Large Vision-Language Models with Abnormal-Aware Feedbackcited by 42
  10. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  11. 2023Closing the Curious Case of Neural Text Degenerationcited by 32
  12. 2022Fine-Grained Distillation for Long Document Retrievalcited by 29
9 more
  1. 2023The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRscited by 29
  2. 2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
  3. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  4. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  5. 2024Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning ratescited by 15
  6. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  7. 2023S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMscited by 7
  8. 2023Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Trackingcited by 5
  9. 2025A survey of textual cyber abuse detection using cutting-edge language models and large language modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agentscited by 9
  2. 2026Multimodal Hidden Markov Models for Persistent Emotional State Trackingcited by 0
  3. 2026An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestrationcited by 0