# IDAS: Intent Discovery with Abstractive Summarization

arXiv: https://arxiv.org/abs/2305.19783 · HTML: https://mlsanity.com/paper/2305.19783/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Effectiveness of Pre-training for Few-shot Intent Classification](https://mlsanity.com/paper/2109.05782/) (2021)
- [TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition](https://mlsanity.com/paper/2110.15063/) (2021)

## Built on by (most cited first, 22 of 22)

- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [Extreme Multi-Label Skill Extraction Training using Large Language Models](https://mlsanity.com/paper/2307.10778/) (2023)
- [Text Clustering as Classification with LLMs](https://mlsanity.com/paper/2410.00927/) (2024)
- [Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues](https://mlsanity.com/paper/2412.09049/) (2024)
- [IntentGPT: Few-shot Intent Discovery with Large Language Models](https://mlsanity.com/paper/2411.10670/) (2024)
- [New Intent Discovery with Attracting and Dispersing Prototype](https://mlsanity.com/paper/2403.16913/) (2024)
- [GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback](https://mlsanity.com/paper/2502.18414/) (2025)
- [In-Context Learning for Extreme Multi-Label Classification](https://mlsanity.com/paper/2401.12178/) (2024)
- [Summaries as Centroids for Interpretable and Scalable Text Clustering](https://mlsanity.com/paper/2502.09667/) (2025)
- [Cequel: Cost-Effective Querying of Large Language Models for Text Clustering](https://mlsanity.com/paper/2504.15640/) (2025)
- [Open-world Multi-label Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2407.05609/) (2024)
- [SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models](https://mlsanity.com/paper/2503.15351/) (2025)
- [LLMs Enable Bag-of-Texts Representations for Short-Text Clustering](https://mlsanity.com/paper/2510.06747/) (2025)
- [Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents](https://mlsanity.com/paper/2603.23518/) (2026)
- [ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models](https://mlsanity.com/paper/2406.13342/) (2024)
- [ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation](https://mlsanity.com/paper/2512.04350/) (2025)
- [How DDAIR you? Disambiguated Data Augmentation for Intent Recognition](https://mlsanity.com/paper/2601.11234/) (2026)
- [Exploring Description-Augmented Dataless Intent Classification](https://mlsanity.com/paper/2407.17862/) (2024)
- [LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels](https://mlsanity.com/paper/2510.14640/) (2025)
- [NILC: Discovering New Intents with LLM-assisted Clustering](https://mlsanity.com/paper/2511.05913/) (2025)
- [Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement](https://mlsanity.com/paper/2606.01255/) (2026)

## Abstract (arXiv)

Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We show that recent competitive methods in intent discovery can be outperformed by clustering utterances based on abstractive summaries, i.e., "labels", that retain the core elements while removing non-essential information. We contribute the IDAS approach, which collects a set of descriptive utterance labels by prompting a Large Language Model, starting from a well-chosen seed set of prototypical utterances, to bootstrap an In-Context Learning procedure to generate labels for non-prototypical utterances. The utterances and their resulting noisy labels are then encoded by a frozen pre-trained encoder, and subsequently clustered to recover the latent intents. For the unsupervised task (without any intent labels) IDAS outperforms the state-of-the-art by up to +7.42% in standard cluster metrics for the Banking, StackOverflow, and Transport datasets. For the semi-supervised task (with labels for a subset of intents) IDAS surpasses 2 recent methods on the CLINC benchmark without even using labeled data.