English
Related papers

Related papers: Crafting Large Language Models for Enhanced Interp…

200 papers

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after…

Computation and Language · Computer Science 2023-11-14 Sean Xie , Soroush Vosoughi , Saeed Hassanpour

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-02-04 Yoshihide Sawada , Keigo Nakamura

Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to…

Machine Learning · Computer Science 2026-05-15 Yingying Fang , Haijie Xu , Shuang Wu , Mariathasan Anish , Guang Yang

Machine learning accelerates molecular property prediction, yet state-of-the-art Large Language Models and Graph Neural Networks operate as black boxes. In drug discovery, where safety is critical, this opacity risks masking false…

Machine Learning · Computer Science 2026-03-03 Oscar Rivera , Ziqing Wang , Matthieu Dagommer , Abhishek Pandey , Kaize Ding

Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides…

Artificial Intelligence · Computer Science 2026-01-21 Hanwei Zhang , Luo Cheng , Rui Wen , Yang Zhang , Lijun Zhang , Holger Hermanns

Concept Bottleneck Models (CBMs) enhance interpretability by introducing a layer of human-understandable concepts between inputs and predictions. While recent methods automate concept generation using Large Language Models (LLMs) and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Delong Zhao , Qiang Huang , Di Yan , Yiqun Sun , Jun Yu

Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However, existing CBMs and their variants have two crucial…

Machine Learning · Computer Science 2023-06-06 Tuomas Oikarinen , Subhro Das , Lam M. Nguyen , Tsui-Wei Weng

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is…

Machine Learning · Computer Science 2026-04-17 Amirhosein Javadi , Tuomas Oikarinen , Tara Javidi , Tsui-Wei Weng

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Nuoye Xiong , Anqi Dong , Ning Wang , Cong Hua , Guangming Zhu , Lin Mei , Peiyi Shen , Liang Zhang

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts and employing Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Nithish Muthuchamy Selvaraj , Xiaobao Guo , Adams Wai-Kin Kong , Alex Kot

Concept Bottleneck Models (CBM) are inherently interpretable models that factor model decisions into human-readable concepts. They allow people to easily understand why a model is failing, a critical feature for high-stakes applications.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Yue Yang , Artemis Panagopoulou , Shenghao Zhou , Daniel Jin , Chris Callison-Burch , Mark Yatskar

The concept bottleneck model (CBM) is an interpretable-by-design framework that makes decisions by first predicting a set of interpretable concepts, and then predicting the class label based on the given concepts. Existing CBMs are trained…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Andong Tan , Fengtao Zhou , Hao Chen

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Townim F. Chowdhury , Vu Minh Hieu Phan , Kewen Liao , Minh-Son To , Yutong Xie , Anton van den Hengel , Johan W. Verjans , Zhibin Liao

Concept Bottleneck Models (CBMs) are interpretable models that route predictions through a layer of human-interpretable concepts. While widely studied in vision and, more recently, in NLP, CBMs remain largely unexplored in multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Pierre Moreau , Emeline Pineau Ferrand , Yann Choho , Benjamin Wong , Annabelle Blangero , Milan Bhan

Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-level concepts (e.g., visible objects and their properties)…

Machine Learning · Computer Science 2026-05-12 Nicola Debole , Pietro Barbiero , Francesco Giannini , Andrea Passerini , Stefano Teso , Emanuele Marconato

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable…

Computation and Language · Computer Science 2024-02-06 Chandan Singh , Jeevana Priya Inala , Michel Galley , Rich Caruana , Jianfeng Gao

Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Hangzhou He , Lei Zhu , Xinliang Zhang , Shuang Zeng , Qian Chen , Yanye Lu

We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike standard RLHF methods that rely on opaque reward functions, CB-RM…

Machine Learning · Computer Science 2025-07-22 Sonia Laguna , Katarzyna Kobalczyk , Julia E. Vogt , Mihaela Van der Schaar

Language Bottleneck Models (LBMs) are proposed to achieve interpretable image recognition by classifying images based on textual concept bottlenecks. However, current LBMs simply list all concepts together as the bottleneck layer, leading…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Jianyang Zhang , Qianli Luo , Guowu Yang , Wenjing Yang , Weide Liu , Guosheng Lin , Fengmao Lv

Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in complex tasks like machine translation, commonsense reasoning, and language understanding. One of the primary reasons for the adaptability of…

Computation and Language · Computer Science 2024-07-12 Nicholas Kroeger , Dan Ley , Satyapriya Krishna , Chirag Agarwal , Himabindu Lakkaraju