# LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification

arXiv: https://arxiv.org/abs/2403.16504 · HTML: https://mlsanity.com/paper/2403.16504/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://mlsanity.com/paper/2105.12907/) (2021)
- [Few-shot Intent Classification and Slot Filling with Retrieved Examples](https://mlsanity.com/paper/2104.05763/) (2021)
- [CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation](https://mlsanity.com/paper/2108.11626/) (2021)
- [Learning to Relate to Previous Turns in Conversational Search](https://mlsanity.com/paper/2306.02553/) (2023)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [User Intent Prediction in Information-seeking Conversations](https://mlsanity.com/paper/1901.03489/) (2019)
- [HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification](https://mlsanity.com/paper/2305.15182/) (2023)
- [BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation](https://mlsanity.com/paper/2301.06745/) (2023)
- [Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks](https://mlsanity.com/paper/2005.02473/) (2020)
- [A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection](https://mlsanity.com/paper/2109.01267/) (2021)

## Built on by (most cited first, 10 of 10)

- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents](https://mlsanity.com/paper/2407.03884/) (2024)
- [Deep Learning Approaches for Multimodal Intent Recognition: A Survey](https://mlsanity.com/paper/2507.22934/) (2025)
- [Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact](https://mlsanity.com/paper/2410.17532/) (2024)
- [Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design](https://mlsanity.com/paper/2411.14214/) (2024)
- [REIC: RAG-Enhanced Intent Classification at Scale](https://mlsanity.com/paper/2506.00210/) (2025)
- [From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification](https://mlsanity.com/paper/2411.14252/) (2024)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation](https://mlsanity.com/paper/2606.28925/) (2026)
- [Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs](https://mlsanity.com/paper/2503.17336/) (2025)

## Abstract (arXiv)

Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. This paper introduces LARA, a Linguistic-Adaptive Retrieval-Augmentation framework to enhance accuracy in multi-turn classification tasks across six languages, accommodating a large number of intents in chatbot interactions. LARA combines a fine-tuned smaller model with a retrieval-augmented mechanism, integrated within the architecture of LLMs. The integration allows LARA to dynamically utilize past dialogues and relevant intents, thereby improving the understanding of the context. Furthermore, our adaptive retrieval techniques bolster the cross-lingual capabilities of LLMs without extensive retraining and fine-tuning. Comprehensive experiments demonstrate that LARA achieves state-of-the-art performance on multi-turn intent classification tasks, enhancing the average accuracy by 3.67% from state-of-the-art single-turn intent classifiers.