# Editable Concept Bottleneck Models

arXiv: https://arxiv.org/abs/2405.15476 · HTML: https://mlsanity.com/paper/2405.15476/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 63 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 42)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Mixed-Privacy Forgetting in Deep Networks](https://mlsanity.com/paper/2012.13431/) (2020)
- [Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis](https://mlsanity.com/paper/1806.03884/) (2018)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020)
- [DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models](https://mlsanity.com/paper/2310.00902/) (2023)
- [FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging](https://mlsanity.com/paper/2012.15781/) (2020)
- [An LLM can Fool Itself: A Prompt-Based Adversarial Attack](https://mlsanity.com/paper/2310.13345/) (2023)
- [Low-Cost High-Power Membership Inference Attacks](https://mlsanity.com/paper/2312.03262/) (2023)
- [Probabilistic Concept Bottleneck Models](https://mlsanity.com/paper/2306.01574/) (2023)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [AI in Finance: Challenges, Techniques and Opportunities](https://mlsanity.com/paper/2107.09051/) (2021)

## Built on by (most cited first, 23 of 23)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [FlipAttack: Jailbreak LLMs via Flipping](https://mlsanity.com/paper/2410.02832/) (2024)
- [Semi-supervised Concept Bottleneck Models](https://mlsanity.com/paper/2406.18992/) (2024)
- [A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2406.12255/) (2024)
- [Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning](https://mlsanity.com/paper/2502.09022/) (2025)
- [Graph Concept Bottleneck Models](https://mlsanity.com/paper/2508.14255/) (2025)
- [Who's Your Judge? On the Detectability of LLM-Generated Judgments](https://mlsanity.com/paper/2509.25154/) (2025)
- [Towards Multi-dimensional Explanation Alignment for Medical Classification](https://mlsanity.com/paper/2410.21494/) (2024)
- [A Comprehensive Survey on the Risks and Limitations of Concept-based Models](https://mlsanity.com/paper/2506.04237/) (2025)
- [Faithful Interpretation for Graph Neural Networks](https://mlsanity.com/paper/2410.06950/) (2024)
- [Stable Vision Concept Transformers for Medical Diagnosis](https://mlsanity.com/paper/2506.05286/) (2025)
- [In-Context Learning Operates as Concept Subspace Learning](https://mlsanity.com/paper/2605.18830/) (2026)
- [Attributing Data for Sharpness-Aware Minimization](https://mlsanity.com/paper/2507.04059/) (2025)
- [Debugging Concept Bottleneck Models through Removal and Retraining](https://mlsanity.com/paper/2509.21385/) (2025)
- [Matryoshka Concept Bottleneck Models](https://mlsanity.com/paper/2605.20612/) (2026)
- [Survival Concept-Based Learning Models](https://mlsanity.com/paper/2502.05950/) (2025)
- [Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment](https://mlsanity.com/paper/2506.07168/) (2025)
- [Towards Interpretable PolSAR Image Classification: Polarimetric Scattering Mechanism Informed Concept Bottleneck and Kolmogorov-Arnold Network](https://mlsanity.com/paper/2507.03315/) (2025)
- [Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models](https://mlsanity.com/paper/2509.17522/) (2025)
- [Bayesian Gated Non-Negative Contrastive Learning](https://mlsanity.com/paper/2605.28441/) (2026)
- [Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks](https://mlsanity.com/paper/2606.19489/) (2026)
- [CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2609.20267/) (2026)
- [Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations](https://mlsanity.com/paper/2609.38625/) (2026)

## Abstract (arXiv)

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a humanunderstandable concept layer. However, most previous studies focused on cases where the data, including concepts, are clean. In many scenarios, we often need to remove/insert some training data or new concepts from trained CBMs for reasons such as privacy concerns, data mislabelling, spurious concepts, and concept annotation errors. Thus, deriving efficient editable CBMs without retraining from scratch remains a challenge, particularly in large-scale applications. To address these challenges, we propose Editable Concept Bottleneck Models (ECBMs). Specifically, ECBMs support three different levels of data removal: concept-label-level, concept-level, and data-level. ECBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for retraining. Experimental results demonstrate the efficiency and adaptability of our ECBMs, affirming their practical value in CBMs.