# Goal-Driven Explainable Clustering via Language Descriptions

arXiv: https://arxiv.org/abs/2305.13749 · HTML: https://mlsanity.com/paper/2305.13749/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Scaling Laws for Generative Mixed-Modal Language Models](https://mlsanity.com/paper/2301.03728/) (2023)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [Automated Phrase Mining from Massive Text Corpora](https://mlsanity.com/paper/1702.04457/) (2017)
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://mlsanity.com/paper/2302.14233/) (2023)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [Describing Differences between Text Distributions with Natural Language](https://mlsanity.com/paper/2201.12323/) (2022)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Towards Open-Set Object Detection and Discovery](https://mlsanity.com/paper/2204.05604/) (2022)
- [Discriminative Topic Mining via Category-Name Guided Text Embedding](https://mlsanity.com/paper/1908.07162/) (2019)
- [Incremental Generalized Category Discovery](https://mlsanity.com/paper/2304.14310/) (2023)
- [Unseen Class Discovery in Open-world Classification](https://mlsanity.com/paper/1801.05609/) (2018)
- [GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language](https://mlsanity.com/paper/2206.15007/) (2022)
- [HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments](https://mlsanity.com/paper/1801.07746/) (2018)
- [WOT-Class: Weakly Supervised Open-world Text Classification](https://mlsanity.com/paper/2305.12401/) (2023)
- [Open-World Weakly-Supervised Object Localization](https://mlsanity.com/paper/2304.08271/) (2023)

## Built on by (most cited first, 30 of 58)

- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Organize the Web: Constructing Domains Enhances Pre-Training Data Curation](https://mlsanity.com/paper/2502.10341/) (2025)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models](https://mlsanity.com/paper/2402.10524/) (2024)
- [CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support](https://mlsanity.com/paper/2407.16148/) (2024)
- [Answer is All You Need: Instruction-following Text Embedding via Answering the Question](https://mlsanity.com/paper/2402.09642/) (2024)
- [EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees](https://mlsanity.com/paper/2503.08893/) (2025)
- [TnT-LLM: Text Mining at Scale with Large Language Models](https://mlsanity.com/paper/2403.12173/) (2024)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [Measuring General Intelligence with Generated Games](https://mlsanity.com/paper/2505.07215/) (2025)
- [Explaining Datasets in Words: Statistical Models with Natural Language Parameters](https://mlsanity.com/paper/2409.08466/) (2024)
- [Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature](https://mlsanity.com/paper/2408.15836/) (2024)
- [Text Clustering as Classification with LLMs](https://mlsanity.com/paper/2410.00927/) (2024)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation](https://mlsanity.com/paper/2307.07099/) (2023)
- [StoryScope: Investigating idiosyncrasies in AI fiction](https://mlsanity.com/paper/2604.03136/) (2026)
- [Automatic Histograms: Leveraging Language Models for Text Dataset Exploration](https://mlsanity.com/paper/2402.14880/) (2024)
- [From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale](https://mlsanity.com/paper/2504.13834/) (2025)
- [The Evolution of LLM Adoption in Industry Data Curation Practices](https://mlsanity.com/paper/2412.16089/) (2024)
- [Summaries as Centroids for Interpretable and Scalable Text Clustering](https://mlsanity.com/paper/2502.09667/) (2025)
- [From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes](https://mlsanity.com/paper/2507.17717/) (2025)
- [Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction](https://mlsanity.com/paper/2502.17541/) (2025)
- [Cequel: Cost-Effective Querying of Large Language Models for Text Clustering](https://mlsanity.com/paper/2504.15640/) (2025)
- [RPM: Reasoning-Level Personalization for Black-Box Large Language Models](https://mlsanity.com/paper/2505.21082/) (2025)
- [Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification](https://mlsanity.com/paper/2507.05010/) (2025)

## Abstract (arXiv)

Unsupervised clustering is widely used to explore large corpora, but existing formulations neither consider the users' goals nor explain clusters' meanings. We propose a new task formulation, "Goal-Driven Clustering with Explanations" (GoalEx), which represents both the goal and the explanations as free-form language descriptions. For example, to categorize the errors made by a summarization system, the input to GoalEx is a corpus of annotator-written comments for system-generated summaries and a goal description "cluster the comments based on why the annotators think the summary is imperfect.''; the outputs are text clusters each with an explanation ("this cluster mentions that the summary misses important context information."), which relates to the goal and precisely explain which comments should (not) belong to a cluster. To tackle GoalEx, we prompt a language model with "[corpus subset] + [goal] + Brainstorm a list of explanations each representing a cluster."; then we classify whether each sample belongs to a cluster based on its explanation; finally, we use integer linear programming to select a subset of candidate clusters to cover most samples while minimizing overlaps. Under both automatic and human evaluation on corpora with or without labels, our method produces more accurate and goal-related explanations than prior methods. We release our data and implementation at https://github.com/ZihanWangKi/GoalEx.