# TnT-LLM: Text Mining at Scale with Large Language Models

arXiv: https://arxiv.org/abs/2403.12173 · HTML: https://mlsanity.com/paper/2403.12173/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 46 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [A Taxonomy of Empathetic Response Intents in Human Social Conversations](https://mlsanity.com/paper/2012.04080/) (2020)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies](https://mlsanity.com/paper/2309.13063/) (2023)
- [Making Large Language Models Better Data Creators](https://mlsanity.com/paper/2310.20111/) (2023)
- [Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations](https://mlsanity.com/paper/2106.02974/) (2021)

## Built on by (most cited first, 26 of 26)

- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [Effects of Prompt Length on Domain-specific Tasks for Large Language Models](https://mlsanity.com/paper/2502.14255/) (2025)
- [Few-shot LLM Synthetic Data with Distribution Matching](https://mlsanity.com/paper/2502.08661/) (2025)
- [LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation](https://mlsanity.com/paper/2407.15351/) (2024)
- [From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale](https://mlsanity.com/paper/2504.13834/) (2025)
- [ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models](https://mlsanity.com/paper/2601.15812/) (2026)
- [Effect of Selection Format on LLM Performance](https://mlsanity.com/paper/2503.06926/) (2025)
- [LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement](https://mlsanity.com/paper/2509.00647/) (2025)
- [Extracting Actionable Insights from Building Energy Data using Vision LLMs on Wavelet and 3D Recurrence Representations](https://mlsanity.com/paper/2509.21934/) (2025)
- [AI in the Enterprise: How People Use M365 Copilot Chat](https://mlsanity.com/paper/2605.23958/) (2026)
- [Interactive Topic Models with Optimal Transport](https://mlsanity.com/paper/2406.19928/) (2024)
- [LegiGPT: Party Politics and Transport Policy with Large Language Model](https://mlsanity.com/paper/2506.16692/) (2025)
- [Generative AI Purpose-built for Social and Mental Health: A Real-World Pilot](https://mlsanity.com/paper/2511.11689/) (2025)
- [How people use Copilot for Health](https://mlsanity.com/paper/2604.15331/) (2026)
- [GEM: Geometric Entropy Mixing for Optimal LLM Data Curation](https://mlsanity.com/paper/2605.26121/) (2026)
- [Semiotic logical hexagon theory for LLM logical reasoning](https://mlsanity.com/paper/2607.21933/) (2026)
- [VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents](https://mlsanity.com/paper/2506.21582/) (2025)
- [Analysis of LLM Performance on AWS Bedrock: Receipt-item Categorisation Case Study](https://mlsanity.com/paper/2604.01615/) (2026)
- [SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models](https://mlsanity.com/paper/2605.00620/) (2026)
- [HoT-SSM:Higher-order Temporal Knowledge Graph Reasoning with State Space Models for Health Care](https://mlsanity.com/paper/2606.05994/) (2026)
- [FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses](https://mlsanity.com/paper/2606.09878/) (2026)
- [An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation](https://mlsanity.com/paper/2608.07023/) (2026)
- [Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations](https://mlsanity.com/paper/2608.08245/) (2026)
- [Principal Trait Analysis: Towards Deriving "Skills" in Human-AI Collaboration](https://mlsanity.com/paper/2608.11460/) (2026)
- [Grounded Skill Synthesis from Code at Scale for Agentic Intelligence](https://mlsanity.com/paper/2609.05571/) (2026)
- [From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale](https://mlsanity.com/paper/2609.19928/) (2026)

## Abstract (arXiv)

Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxonomies and building text-based label classifiers still rely heavily on domain expertise and manual curation, making the process expensive and time-consuming. This is particularly challenging when the label space is under-specified and large-scale data annotations are unavailable. In this paper, we address these challenges with Large Language Models (LLMs), whose prompt-based interface facilitates the induction and use of large-scale pseudo labels. We propose TnT-LLM, a two-phase framework that employs LLMs to automate the process of end-to-end label generation and assignment with minimal human effort for any given use-case. In the first phase, we introduce a zero-shot, multi-stage reasoning approach which enables LLMs to produce and refine a label taxonomy iteratively. In the second phase, LLMs are used as data labelers that yield training samples so that lightweight supervised classifiers can be reliably built, deployed, and served at scale. We apply TnT-LLM to the analysis of user intent and conversational domain for Bing Copilot (formerly Bing Chat), an open-domain chat-based search engine. Extensive experiments using both human and automatic evaluation metrics demonstrate that TnT-LLM generates more accurate and relevant label taxonomies when compared against state-of-the-art baselines, and achieves a favorable balance between accuracy and efficiency for classification at scale. We also share our practical experiences and insights on the challenges and opportunities of using LLMs for large-scale text mining in real-world applications.