# Intent Detection in the Age of LLMs

arXiv: https://arxiv.org/abs/2410.01627 · HTML: https://mlsanity.com/paper/2410.01627/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [Effectiveness of Pre-training for Few-shot Intent Classification](https://mlsanity.com/paper/2109.05782/) (2021)
- [HINT3: Raising the bar for Intent Detection in the Wild](https://mlsanity.com/paper/2009.13833/) (2020)

## Built on by (most cited first, 25 of 25)

- [LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System](https://mlsanity.com/paper/2501.15749/) (2025)
- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)
- [On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation](https://mlsanity.com/paper/2502.12923/) (2025)
- [RECAP: REwriting Conversations for Intent Understanding in Agentic Planning](https://mlsanity.com/paper/2509.04472/) (2025)
- [Toward Super Agent System with Hybrid AI Routers](https://mlsanity.com/paper/2504.10519/) (2025)
- [Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching](https://mlsanity.com/paper/2510.26702/) (2025)
- [Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation](https://mlsanity.com/paper/2505.18556/) (2025)
- [Agentic Coding Needs Proactivity, Not Just Autonomy](https://mlsanity.com/paper/2605.06717/) (2026)
- [Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations](https://mlsanity.com/paper/2507.22289/) (2025)
- [How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting](https://mlsanity.com/paper/2507.22923/) (2025)
- [Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering](https://mlsanity.com/paper/2605.12645/) (2026)
- [Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing](https://mlsanity.com/paper/2507.01541/) (2025)
- [Beyond Context: Large Language Models' Failure to Grasp Users' Intent](https://mlsanity.com/paper/2512.21110/) (2025)
- [How DDAIR you? Disambiguated Data Augmentation for Intent Recognition](https://mlsanity.com/paper/2601.11234/) (2026)
- [Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI](https://mlsanity.com/paper/2605.02682/) (2026)
- [Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes](https://mlsanity.com/paper/2608.02415/) (2026)
- [Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings](https://mlsanity.com/paper/2503.05620/) (2025)
- [Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions](https://mlsanity.com/paper/2510.08576/) (2025)
- [DROID: Dual Representation for Out-of-Scope Intent Detection](https://mlsanity.com/paper/2510.14110/) (2025)
- [IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference](https://mlsanity.com/paper/2603.03325/) (2026)
- [Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue](https://mlsanity.com/paper/2605.12856/) (2026)
- [SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding](https://mlsanity.com/paper/2606.25552/) (2026)
- [A Multi-cluster Boundary Learning Method for Out-of-Scope Intent Detection via MiniLM Embedding](https://mlsanity.com/paper/2607.07974/) (2026)
- [When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems](https://mlsanity.com/paper/2608.20371/) (2026)
- [Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations](https://mlsanity.com/paper/2608.28926/) (2026)

## Abstract (arXiv)

Intent detection is a critical component of task-oriented dialogue systems (TODS) which enables the identification of suitable actions to address user utterances at each dialog turn. Traditional approaches relied on computationally efficient supervised sentence transformer encoder models, which require substantial training data and struggle with out-of-scope (OOS) detection. The emergence of generative large language models (LLMs) with intrinsic world knowledge presents new opportunities to address these challenges. In this work, we adapt 7 SOTA LLMs using adaptive in-context learning and chain-of-thought prompting for intent detection, and compare their performance with contrastively fine-tuned sentence transformer (SetFit) models to highlight prediction quality and latency tradeoff. We propose a hybrid system using uncertainty based routing strategy to combine the two approaches that along with negative data augmentation results in achieving the best of both worlds ( i.e. within 2% of native LLM accuracy with 50% less latency). To better understand LLM OOS detection capabilities, we perform controlled experiments revealing that this capability is significantly influenced by the scope of intent labels and the size of the label space. We also introduce a two-step approach utilizing internal LLM representations, demonstrating empirical gains in OOS detection accuracy and F1-score by >5% for the Mistral-7B model.