mlsanityData to 7 Oct 2026

IDAS: Intent Discovery with Abstractive Summarization

arXiv 2305.19783 ↗First posted 31 May 2023cs.CLcited by 22

Not on the map. Why?

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

24 of 43 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  7. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  8. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  9. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  10. 2021MetaICL: Learning to Learn In Contextcited by 450
  11. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  12. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
12 more
  1. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  2. 2015Skip-Thought Vectorscited by 321
  3. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  4. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  5. 2021Meta-learning via Language Model In-context Tuningcited by 163
  6. 2021Supporting Clustering with Contrastive Learningcited by 90
  7. 2022Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrationscited by 70
  8. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  9. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  10. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  11. 2021Effectiveness of Pre-training for Few-shot Intent Classificationcited by 27
  12. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 8; 2026: 3.

22 papers.

Sort:

By area:

  1. 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
  2. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  3. 2023Extreme Multi-Label Skill Extraction Training using Large Language Modelscited by 17
  4. 2024Text Clustering as Classification with LLMscited by 16
  5. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  6. 2024IntentGPT: Few-shot Intent Discovery with Large Language Modelscited by 8
  7. 2024New Intent Discovery with Attracting and Dispersing Prototypecited by 6
  8. 2025GLEAN: Active Generalized Category Discovery with Diverse LLM Feedbackcited by 6
  9. 2024In-Context Learning for Extreme Multi-Label Classificationcited by 4
  10. 2025Summaries as Centroids for Interpretable and Scalable Text Clusteringcited by 4
  11. 2025Cequel: Cost-Effective Querying of Large Language Models for Text Clusteringcited by 3
  12. 2024Open-world Multi-label Text Classification with Extremely Weak Supervisioncited by 2
10 more
  1. 2025SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Modelscited by 2
  2. 2025LLMs Enable Bag-of-Texts Representations for Short-Text Clusteringcited by 2
  3. 2026Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agentscited by 2
  4. 2024ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Modelscited by 1
  5. 2025ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptationcited by 1
  6. 2026How DDAIR you? Disambiguated Data Augmentation for Intent Recognitioncited by 1
  7. 2024Exploring Description-Augmented Dataless Intent Classificationcited by 0
  8. 2025LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labelscited by 0
  9. 2025NILC: Discovering New Intents with LLM-assisted Clusteringcited by 0
  10. 2026Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinementcited by 0