# Continual Dialogue State Tracking via Reason-of-Select Distillation

arXiv: https://arxiv.org/abs/2408.09846 · HTML: https://mlsanity.com/paper/2408.09846/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 19 Aug 2024.

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

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [SCOTT: Self-Consistent Chain-of-Thought Distillation](https://mlsanity.com/paper/2305.01879/) (2023)
- [MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation](https://mlsanity.com/paper/2104.00773/) (2021)
- [Continual Learning in Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2012.15504/) (2020)
- [Continual Prompt Tuning for Dialog State Tracking](https://mlsanity.com/paper/2203.06654/) (2022)
- [ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?](https://mlsanity.com/paper/2306.01386/) (2023)
- [Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking](https://mlsanity.com/paper/2107.08173/) (2021)
- [Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals](https://mlsanity.com/paper/2309.08949/) (2023)
- [Continual Dialogue State Tracking via Example-Guided Question Answering](https://mlsanity.com/paper/2305.13721/) (2023)

## Built on by (most cited first, 8 of 8)

- [Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL](https://mlsanity.com/paper/2602.13035/) (2026)
- [Recurrent Knowledge Identification and Fusion for Language Model Continual Learning](https://mlsanity.com/paper/2502.17510/) (2025)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning](https://mlsanity.com/paper/2601.03938/) (2026)
- [GeoEdit: Geometric Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2502.19953/) (2025)
- [AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning](https://mlsanity.com/paper/2509.17348/) (2025)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection](https://mlsanity.com/paper/2409.11114/) (2024)

## Abstract (arXiv)

An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting catastrophic forgetting, along with a critical capability loss termed the "Value Selection Quandary." To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel 'meta-reasoning' capability. Meta-reasoning employs an enhanced multi-domain perspective, combining fragments of meta-knowledge from domain-specific dialogues during continual learning. This transcends traditional single-perspective reasoning. The domain bootstrapping process enhances the model's ability to dissect intricate dialogues from multiple possible values. Its domain-agnostic property aligns data distribution across different domains, effectively mitigating forgetting. Additionally, two novel improvements, "multi-value resolution" strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DST-specific selection chains and mitigating hallucinations in teachers' reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method. The source code is provided for reproducibility.