# Explaining Datasets in Words: Statistical Models with Natural Language Parameters

arXiv: https://arxiv.org/abs/2409.08466 · HTML: https://mlsanity.com/paper/2409.08466/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 61 references that are in the map.
- First posted on arXiv 13 Sep 2024.

## Builds on (most cited first, 30 of 41)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [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)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Learning with Latent Language](https://mlsanity.com/paper/1711.00482/) (2017)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [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)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [Describing Differences between Text Distributions with Natural Language](https://mlsanity.com/paper/2201.12323/) (2022)
- [Describing Differences in Image Sets with Natural Language](https://mlsanity.com/paper/2312.02974/) (2023)

## Built on by (most cited first, 21 of 21)

- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [Idiosyncrasies in Large Language Models](https://mlsanity.com/paper/2502.12150/) (2025)
- [EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees](https://mlsanity.com/paper/2503.08893/) (2025)
- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [Organizing Unstructured Image Collections using Natural Language](https://mlsanity.com/paper/2410.05217/) (2024)
- [Chunky Post-Training: Data Driven Failures of Generalization](https://mlsanity.com/paper/2602.05910/) (2026)
- [The Vendiscope: An Algorithmic Microscope For Data Collections](https://mlsanity.com/paper/2502.10828/) (2025)
- [Automatically Finding Reward Model Biases](https://mlsanity.com/paper/2602.15222/) (2026)
- [Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction](https://mlsanity.com/paper/2502.17541/) (2025)
- [ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering](https://mlsanity.com/paper/2507.00828/) (2025)
- [ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making](https://mlsanity.com/paper/2602.19458/) (2026)
- [Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images](https://mlsanity.com/paper/2504.08727/) (2025)
- [Automated Concept Discovery for LLM-as-a-Judge Preference Analysis](https://mlsanity.com/paper/2603.03319/) (2026)
- [Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance](https://mlsanity.com/paper/2604.17650/) (2026)
- [RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models](https://mlsanity.com/paper/2510.19698/) (2025)
- [GenZ: Foundational models as latent variable generators within traditional statistical models](https://mlsanity.com/paper/2512.24834/) (2025)
- [Discovering Implicit Large Language Model Alignment Objectives](https://mlsanity.com/paper/2602.15338/) (2026)
- [Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates](https://mlsanity.com/paper/2606.03029/) (2026)
- [On the Role of Citations in Preference Data](https://mlsanity.com/paper/2608.21376/) (2026)
- [What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language](https://mlsanity.com/paper/2610.01627/) (2026)

## Abstract (arXiv)

To make sense of massive data, we often fit simplified models and then interpret the parameters; for example, we cluster the text embeddings and then interpret the mean parameters of each cluster. However, these parameters are often high-dimensional and hard to interpret. To make model parameters directly interpretable, we introduce a family of statistical models -- including clustering, time series, and classification models -- parameterized by natural language predicates. For example, a cluster of text about COVID could be parameterized by the predicate "discusses COVID". To learn these statistical models effectively, we develop a model-agnostic algorithm that optimizes continuous relaxations of predicate parameters with gradient descent and discretizes them by prompting language models (LMs). Finally, we apply our framework to a wide range of problems: taxonomizing user chat dialogues, characterizing how they evolve across time, finding categories where one language model is better than the other, clustering math problems based on subareas, and explaining visual features in memorable images. Our framework is highly versatile, applicable to both textual and visual domains, can be easily steered to focus on specific properties (e.g. subareas), and explains sophisticated concepts that classical methods (e.g. n-gram analysis) struggle to produce.