# Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck

arXiv: https://arxiv.org/abs/2310.19660 · HTML: https://mlsanity.com/paper/2310.19660/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 78 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization](https://mlsanity.com/paper/1906.03741/) (2019)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning](https://mlsanity.com/paper/2009.10277/) (2020)
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://mlsanity.com/paper/2302.14233/) (2023)
- [Investigating Societal Biases in a Poetry Composition System](https://mlsanity.com/paper/2011.02686/) (2020)
- [SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers](https://mlsanity.com/paper/2103.12279/) (2021)
- [Human Uncertainty in Concept-Based AI Systems](https://mlsanity.com/paper/2303.12872/) (2023)

## Built on by (most cited first, 22 of 22)

- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [Position: Use Sparse Autoencoders to Discover Unknowns](https://mlsanity.com/paper/2506.23845/) (2025)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [MiRAGeNews: Multimodal Realistic AI-Generated News Detection](https://mlsanity.com/paper/2410.09045/) (2024)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition](https://mlsanity.com/paper/2508.08274/) (2025)
- [Accelerating Social Science Research via Agentic Hypothesization and Experimentation](https://mlsanity.com/paper/2602.07983/) (2026)
- [Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization](https://mlsanity.com/paper/2502.13632/) (2025)
- [Adaptive Test-Time Intervention for Concept Bottleneck Models](https://mlsanity.com/paper/2503.06730/) (2025)
- [ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts](https://mlsanity.com/paper/2511.11883/) (2025)
- [Mitigating Label Bias with Interpretable Rubric Embeddings](https://mlsanity.com/paper/2605.21455/) (2026)
- [Iterative Learning of Computable Phenotypes for Treatment Resistant Hypertension using Large Language Models](https://mlsanity.com/paper/2508.05581/) (2025)
- [When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate](https://mlsanity.com/paper/2512.03578/) (2025)
- [GenZ: Foundational models as latent variable generators within traditional statistical models](https://mlsanity.com/paper/2512.24834/) (2025)
- [Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection](https://mlsanity.com/paper/2602.04607/) (2026)
- [Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition](https://mlsanity.com/paper/2604.24170/) (2026)
- [Interpretable Discriminative Text Representations via Agreement and Label Disentanglement](https://mlsanity.com/paper/2605.20693/) (2026)
- [Principal Trait Analysis: Towards Deriving "Skills" in Human-AI Collaboration](https://mlsanity.com/paper/2608.11460/) (2026)
- [J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules](https://mlsanity.com/paper/2608.17063/) (2026)
- [EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues](https://mlsanity.com/paper/2609.27043/) (2026)
- [Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressions](https://mlsanity.com/paper/2609.34326/) (2026)
- [AnyBottle: A Recipe to Only Keep the Concepts You Really Need](https://mlsanity.com/paper/2610.08552/) (2026)

## Abstract (arXiv)

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically interpretable text classification framework that offers both global and local explanations. Rather than directly predicting the output label, TBM predicts categorical values for a sparse set of salient concepts and uses a linear layer over those concept values to produce the final prediction. These concepts can be automatically discovered and measured by a Large Language Model (LLM) without the need for human curation. Experiments on 12 diverse text understanding datasets demonstrate that TBM can rival the performance of black-box baselines such as few-shot GPT-4 and finetuned DeBERTa while falling short against finetuned GPT-3.5. Comprehensive human evaluation validates that TBM can generate high-quality concepts relevant to the task, and the concept measurement aligns well with human judgments, suggesting that the predictions made by TBMs are interpretable. Overall, our findings suggest that TBM is a promising new framework that enhances interpretability with minimal performance tradeoffs.