paper-with-me

Papers

Editable Concept Bottleneck Models

2024-05-24 · Lijie Hu, Chenyang Ren, Zhengyu Hu, Hongbin Lin, Cheng-Long Wang, Hui Xiong, Jingfeng Zhang, Di Wang

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.

📄 PDF Abstract BibTeX arXiv:2405.15476

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models

2025-06-02 · Yiwen Jiang, Deval Mehta, Wei Feng, ZongYuan Ge

Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts. Recent advances in CBMs have used Large Language Models (LLMs) to generate candidate conc…

image-classificationImage Classification

Controllable Concept Bottleneck Models

2026-01-01 · Hongbin Lin, Chenyang Ren, Juangui Xu, Zhengyu Hu 외 arxiv

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios…

Incremental Learning

EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading

2025-12-23 · Kumar Satvik Chaudhary, Chengshuai Zhao, Fan Zhang, Garima Agrawal 외 arxiv

Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In educational settings, instructors must be …

Automated Essay Scoring

PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck

2024-03-08 · Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon 외

CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. Therefore, they perform poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scienti…

Editable User Profiles for Controllable Text Recommendation

2023-04-09 · Sheshera Mysore, Mahmood Jasim, Andrew McCallum, Hamed Zamani

Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendatio…

Recommendation SystemsRetrieval