Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues

• URL: http://arxiv.org/abs/2412.09049v2
• Date: Wed, 19 Mar 2025 06:14:04 GMT
• Title: Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues
• Authors: Mengze Hong, Di Jiang, Yuanfeng Song, Lu Wang, Wailing Ng, Yanjie Sun, Chen Jason Zhang, Qing Li,
• Abstract summary: This paper investigates the effectiveness of fine-tuned.<n>LLMs in semantic coherence evaluation and intent cluster naming.<n>It also proposes an.<n>LLM-ITL clustering algorithm that facilitates the iterative discovery of.<n>coherent intent clusters.
• Score: 18.744211667479995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discovering customer intentions in dialogue conversations is crucial for automated service agents. Yet, existing intent clustering methods often fail to align with human perceptions due to the heavy reliance on embedding distance metrics and sentence embeddings. To address these limitations, we propose integrating the semantic understanding capabilities of LLMs into an $\textbf{LLM-in-the-loop (LLM-ITL)}$ intent clustering framework. Specifically, this paper (1) investigates the effectiveness of fine-tuned LLMs in semantic coherence evaluation and intent cluster naming, achieving over 95% accuracy; (2) designs an LLM-ITL clustering algorithm that facilitates the iterative discovery of coherent intent clusters; and (3) proposes task-specific techniques tailored for customer service dialogue intent clustering. Since existing English benchmarks pose limited semantic diversity and intent labels, we introduced a comprehensive Chinese dialogue intent dataset, comprising over 100,000 real customer service calls and 1,507 human-annotated intent clusters. The proposed approaches significantly outperformed LLM-guided baselines, achieving notable improvements in clustering quality and a 12% boost in the downstream intent classification task. Combined with several best practices, our findings highlight the potential of LLM-in-the-loop techniques for scalable and human-aligned problem-solving. Sample code and datasets are available at: https://anonymous.4open.science/r/Dial-in-LLM-0410.

Related papers

• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system. It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric [0.5671051073036456]
  Keywords-based Utterance Level Clustering Quality (KULCQ) is an unsupervised metric that leverages keyword analysis to evaluate clustering quality. Our results show that KULCQ better captures semantic relationships in conversational data while maintaining consistency with geometric clustering principles.
  arXiv  Detail & Related papers  (2024-11-15T00:21:02Z)
• Text Clustering as Classification with LLMs [6.030435811868953]
  This study presents a novel framework for text clustering that effectively leverages the in-context learning capacity of Large Language Models (LLMs) Instead of fine-tuning embedders, we propose to transform the text clustering into a classification task via LLM. Our framework has been experimentally proven to achieve comparable or superior performance to state-of-the-art clustering methods.
  arXiv  Detail & Related papers  (2024-09-30T16:57:34Z)
• Fine-tuning Multimodal Large Language Models for Product Bundling [53.01642741096356]
  We introduce Bundle-MLLM, a novel framework that fine-tunes large language models (LLMs) through a hybrid item tokenization approach. Specifically, we integrate textual, media, and relational data into a unified tokenization, introducing a soft separation token to distinguish between textual and non-textual tokens. We propose a progressive optimization strategy that fine-tunes LLMs for disentangled objectives: 1) learning bundle patterns and 2) enhancing multimodal semantic understanding specific to product bundling.
  arXiv  Detail & Related papers  (2024-07-16T13:30:14Z)
• ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models [5.011816280731356]
  We propose a simple yet effective method to contextualize a task toward a specific large language model (LLMs) We show the effectiveness of this approach in text clustering tasks, and also highlight the importance of the contextualization through examples of the above procedure.
  arXiv  Detail & Related papers  (2024-06-19T08:48:05Z)
• Context-Aware Clustering using Large Language Models [20.971691166166547]
  We propose CACTUS (Context-Aware ClusTering with aUgmented triplet losS) for efficient and effective supervised clustering of entity subsets. This paper introduces a novel approach towards clustering entity subsets using Large Language Models (LLMs) by capturing context via a scalable inter-entity attention mechanism.
  arXiv  Detail & Related papers  (2024-05-02T03:50:31Z)
• RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition [78.97487780589574]
  Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories. This paper introduces a Retrieving And Ranking augmented method for MLLMs. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base.
  arXiv  Detail & Related papers  (2024-03-20T17:59:55Z)
• End-to-end Learnable Clustering for Intent Learning in Recommendation [54.157784572994316]
  We propose a novel intent learning method termed underlineELCRec. It unifies behavior representation learning into an underlineEnd-to-end underlineLearnable underlineClustering framework. We deploy this method on the industrial recommendation system with 130 million page views and achieve promising results.
  arXiv  Detail & Related papers  (2024-01-11T15:22:55Z)
• Human-Instruction-Free LLM Self-Alignment with Limited Samples [64.69906311787055]
  We propose an algorithm that can self-align large language models (LLMs) iteratively without active human involvement. Unlike existing works, our algorithm relies on neither human-crafted instructions nor labeled rewards, significantly reducing human involvement. We show that our method can unlock the LLMs' self-generalization ability to perform alignment with near-zero human supervision.
  arXiv  Detail & Related papers  (2024-01-06T14:00:12Z)
• Large Language Models Enable Few-Shot Clustering [88.06276828752553]
  We show that large language models can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality.
  arXiv  Detail & Related papers  (2023-07-02T09:17:11Z)
• OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
  We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs. Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
  arXiv  Detail & Related papers  (2023-05-24T10:08:04Z)
• CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering [16.08402937918212]
  We propose a novel Classification-Enhanced Iterative Learning framework for short text clustering. In each iteration, we first adopt a language model to retrieve the initial text representations. After strict data filtering and aggregation processes, samples with clean category labels are retrieved, which serve as supervision information. Finally, the updated language model with improved representation ability is used to enhance clustering in the next iteration.
  arXiv  Detail & Related papers  (2023-04-20T14:04:31Z)
• Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue [8.07809100513473]
  This work investigates unsupervised approaches to overcome challenges in designing task-oriented dialog schema. We postulate there are two salient factors for automatic induction of intents: (1) clustering algorithm for intent labeling and (2) user utterance embedding space. Pretrained MiniLM with Agglomerative clustering shows significant improvement in NMI, ARI, F1, accuracy and example coverage in intent induction tasks.
  arXiv  Detail & Related papers  (2022-12-05T04:37:22Z)
• You Never Cluster Alone [150.94921340034688]
  We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation. We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
  arXiv  Detail & Related papers  (2021-06-03T14:59:59Z)
• Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
  Existing scalable hierarchical clustering methods sacrifice quality for speed. We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
  arXiv  Detail & Related papers  (2020-10-22T15:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.