# Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM

arXiv: https://arxiv.org/abs/2404.12259 · HTML: https://mlsanity.com/paper/2404.12259/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 76 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [Accelerated Hierarchical Density Clustering](https://mlsanity.com/paper/1705.07321/) (2017)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings](https://mlsanity.com/paper/1904.01596/) (2019)
- [Designing Toxic Content Classification for a Diversity of Perspectives](https://mlsanity.com/paper/2106.04511/) (2021)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words](https://mlsanity.com/paper/2205.05092/) (2022)
- [Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models](https://mlsanity.com/paper/2305.11483/) (2023)
- [Embedding Democratic Values into Social Media AIs via Societal Objective Functions](https://mlsanity.com/paper/2307.13912/) (2023)
- [Unpacking the Expressed Consequences of AI Research in Broader Impact Statements](https://mlsanity.com/paper/2105.04760/) (2021)
- [Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design](https://mlsanity.com/paper/2303.02884/) (2023)
- [Scholastic: Graphical Human-Al Collaboration for Inductive and Interpretive Text Analysis](https://mlsanity.com/paper/2208.06133/) (2022)
- [Supporting Serendipity: Opportunities and Challenges for Human-AI Collaboration in Qualitative Analysis](https://mlsanity.com/paper/2102.03702/) (2021)
- [Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections](https://mlsanity.com/paper/1908.00475/) (2019)
- [Hypothesis Formalization: Empirical Findings, Software Limitations, and Design Implications](https://mlsanity.com/paper/2104.02712/) (2021)
- [GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks](https://mlsanity.com/paper/2207.08320/) (2022)
- [Breaking Out of the Ivory Tower: A Large-scale Analysis of Patent Citations to HCI Research](https://mlsanity.com/paper/2301.13431/) (2023)
- [Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships](https://mlsanity.com/paper/2201.02705/) (2022)

## Built on by (most cited first, 30 of 78)

- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions](https://mlsanity.com/paper/2504.15236/) (2025)
- [Can Unconfident LLM Annotations Be Used for Confident Conclusions?](https://mlsanity.com/paper/2408.15204/) (2024)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [Aligning Language Models with Demonstrated Feedback](https://mlsanity.com/paper/2406.00888/) (2024)
- [SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs](https://mlsanity.com/paper/2506.05598/) (2025)
- ['Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants](https://mlsanity.com/paper/2409.19430/) (2024)
- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data](https://mlsanity.com/paper/2510.26202/) (2025)
- [The emergence of Large Language Models (LLM) as a tool in literature reviews: an LLM automated systematic review](https://mlsanity.com/paper/2409.04600/) (2024)
- [Explaining Datasets in Words: Statistical Models with Natural Language Parameters](https://mlsanity.com/paper/2409.08466/) (2024)
- [Bayesian Concept Bottleneck Models with LLM Priors](https://mlsanity.com/paper/2410.15555/) (2024)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [HICode: Hierarchical Inductive Coding with LLMs](https://mlsanity.com/paper/2509.17946/) (2025)
- [DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration](https://mlsanity.com/paper/2408.00447/) (2024)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models](https://mlsanity.com/paper/2505.19240/) (2025)
- [From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale](https://mlsanity.com/paper/2504.13834/) (2025)
- [ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemaking](https://mlsanity.com/paper/2504.14406/) (2025)
- [The Evolution of LLM Adoption in Industry Data Curation Practices](https://mlsanity.com/paper/2412.16089/) (2024)
- [Generative Interfaces for Language Models](https://mlsanity.com/paper/2508.19227/) (2025)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors](https://mlsanity.com/paper/2409.18203/) (2024)
- [Intent-Aware Schema Generation And Refinement For Literature Review Tables](https://mlsanity.com/paper/2507.19521/) (2025)
- [Characterizing Web Search in The Age of Generative AI](https://mlsanity.com/paper/2510.11560/) (2025)
- [MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections](https://mlsanity.com/paper/2502.00322/) (2025)
- [Thoughtful Adoption of NLP for Civic Participation: Understanding Differences Among Policymakers](https://mlsanity.com/paper/2410.22937/) (2024)
- [Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction](https://mlsanity.com/paper/2502.17541/) (2025)

## Abstract (arXiv)

Data analysts have long sought to turn unstructured text data into meaningful concepts. Though common, topic modeling and clustering focus on lower-level keywords and require significant interpretative work. We introduce concept induction, a computational process that instead produces high-level concepts, defined by explicit inclusion criteria, from unstructured text. For a dataset of toxic online comments, where a state-of-the-art BERTopic model outputs "women, power, female," concept induction produces high-level concepts such as "Criticism of traditional gender roles" and "Dismissal of women's concerns." We present LLooM, a concept induction algorithm that leverages large language models to iteratively synthesize sampled text and propose human-interpretable concepts of increasing generality. We then instantiate LLooM in a mixed-initiative text analysis tool, enabling analysts to shift their attention from interpreting topics to engaging in theory-driven analysis. Through technical evaluations and four analysis scenarios ranging from literature review to content moderation, we find that LLooM's concepts improve upon the prior art of topic models in terms of quality and data coverage. In expert case studies, LLooM helped researchers to uncover new insights even from familiar datasets, for example by suggesting a previously unnoticed concept of attacks on out-party stances in a political social media dataset.