mlsanityData to 14 Oct 2026

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models

arXiv 2502.11100 ↗First posted 16 Feb 2025cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

30 of 51 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  10. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  11. 2020Concept Bottleneck Modelscited by 1,032
  12. 2022A Survey on In-context Learningcited by 721
18 more
  1. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 716
  2. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
  3. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  4. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 218
  5. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  6. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  7. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 125
  8. 2024Small Language Models: Survey, Measurements, and Insightscited by 112
  9. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 109
  10. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  11. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  12. 2022Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approachescited by 39
  13. 2023Interpreting Pretrained Language Models via Concept Bottleneckscited by 33
  14. 2023Using Captum to Explain Generative Language Modelscited by 33
  15. 2023Learning to Intervene on Concept Bottleneckscited by 29
  16. 2022Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectorscited by 14
  17. 2024Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanationscited by 8
  18. 2024Crafting Large Language Models for Enhanced Interpretabilitycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025In-Distribution Steering: Balancing Control and Coherence in Language Model Generationcited by 9
  2. 2026Matryoshka Concept Bottleneck Modelscited by 2
  3. 2025NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignmentcited by 0
  4. 2026Towards Faithful Multimodal Concept Bottleneck Modelscited by 0
  5. 2026Mimir: Large-scale Multilingual Concept Modelingcited by 0
  6. 2026The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generationcited by 0
  7. 2026Evolving LLM-Generated Features for Interpretable Classificationcited by 0