# Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries

arXiv: https://arxiv.org/abs/2402.13043 · HTML: https://mlsanity.com/paper/2402.13043/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 30 of 36)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation](https://mlsanity.com/paper/2305.16938/) (2023)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context](https://mlsanity.com/paper/1911.10484/) (2019)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [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)
- [Efficient Dialogue State Tracking by Selectively Overwriting Memory](https://mlsanity.com/paper/1911.03906/) (2019)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking](https://mlsanity.com/paper/2105.04222/) (2021)
- [Description-Driven Task-Oriented Dialog Modeling](https://mlsanity.com/paper/2201.08904/) (2022)

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

- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues](https://mlsanity.com/paper/2507.06910/) (2025)
- [Intent-driven In-context Learning for Few-shot Dialogue State Tracking](https://mlsanity.com/paper/2412.03270/) (2024)
- [PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback](https://mlsanity.com/paper/2508.15456/) (2025)
- [Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs](https://mlsanity.com/paper/2512.06869/) (2025)
- [S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling](https://mlsanity.com/paper/2608.14029/) (2026)
- [Role-aware Heuristic Episodic Attention for Conversational LLMs](https://mlsanity.com/paper/2610.00958/) (2026)

## Abstract (arXiv)

Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search keys and queries, and a retriever is fine-tuned with annotated dialogues to achieve superior performance. However, the approach is less suited for scaling to new domains or new annotation languages, where fine-tuning data is unavailable. To address this problem, we handle the task of conversation retrieval based on text summaries of the conversations. A LLM-based conversation summarizer is adopted for query and key generation, which enables effective maximum inner product search. To avoid the extra inference cost brought by LLM-based conversation summarization, we further distill a light-weight conversation encoder which produces query embeddings without decoding summaries for test conversations. We validate our retrieval approach on MultiWOZ datasets with GPT-Neo-2.7B and LLaMA-7B/30B. The experimental results show a significant improvement over relevant baselines in real few-shot DST settings.