While state-of-the-art language models (LMs) surpass most humans in certain domains, their reasoning remains largely opaque, reducing trust and increasing the risk of deception and hallucination. We introduce the Prototype Transformer (ProtoT), an autoregressive LM architecture that replaces the quadratic-cost self-attention module of the Transformer with a linear-cost module based on prototypes, which are learned parameter vectors. In ProtoT, prototypes create communication channels that aggregate contextual information at different time scales. We show that this structure leads prototypes to automatically capture nameable concepts, such as "woman", during training, offering a path toward interpreting model reasoning and making targeted edits to model behavior. Compared with baselines, ProtoT scales well with model and data size, is robust to input perturbations, and performs well on text generation and downstream tasks, including GLUE. These results suggest that ProtoT is a promising step toward autoregressive language models that are more interpretable by design.
Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes
State Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学);School of Artificial Intelligence, Nanjing University(人工智能学院,南京大学)
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis
Christian Doppler Laboratory for Artificial Intelligence in Retina(人工智能在视网膜领域的克里斯蒂安·多普勒实验室);Institute of Artificial Intelligence(人工智能研究所);Center for Medical Data Science(医学数据科学中心);Medical University of Vienna(维也纳医学大学)
ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography
Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark(应用数学与计算机科学系,丹麦技术大学,Kongens Lyngby);Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada(电气与计算机工程系,不列颠哥伦比亚大学,温哥华,BC,加拿大);Vancouver General Hospital, Vancouver, BC, Canada(温哥华总医院,温哥华,BC,加拿大)
HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection
Laboratoire Hubert Curien, UMR CNRS 5516(于贝尔·居里实验室,法国国家科学研究中心5516联合研究单位);Université Lumière Lyon 2(里昂第二大学);Université Claude Bernard Lyon 1(克洛德·贝尔纳里昂第一大学);ERIC, Lyon(里昂ERIC实验室);École Centrale de Lyon(里昂中央理工学院);LIRIS CNRS UMR 5205(LIRIS实验室,法国国家科学研究中心5205联合研究单位)
Interpretable Medical Image Classification using Prototype Learning and Privileged Information
Experimental Radiology, University Hospital Ulm, Germany(实验放射学,乌尔姆大学医院,德国);Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany(诊断与介入放射学系,乌尔姆大学医院,德国);i2SouI - Innovative Imaging in Surgical Oncology Ulm, University Hospital Ulm, Germany(i2SouI - 精准影像学在手术肿瘤学中的创新应用,乌尔姆大学医院,德国)
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer
SenseTime Research(商汤科技研究院);University of Toronto(多伦多大学);The Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer
Anhui University(安徽大学);Monash University(莫纳什大学);Fuzhou University(福州大学);University of Hong Kong(香港大学);University of Nottingham Malaysia Campus(诺丁汉大学马来西亚校区);University of Sassari(萨萨里大学)
A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Disease Detection from Retinal Fundus Images
Hertie Institute for AI in Brain Health, University of Tübingen, Germany(人工智能与脑健康赫尔特研究所,图宾根大学,德国);Tübingen AI Center, University of Tübingen, Germany(图宾根人工智能中心,图宾根大学,德国)
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Department of Computer Science and Engineering, Sungkyunkwan University(计算机科学与工程系,全州大学);Department of Computer Science, Loyola University(计算机科学系,洛伊拉大学)
A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
The Ohio State University(俄亥俄州立大学);Amazon Alexa(亚马逊 Alexa);Virginia Tech(弗吉尼亚理工大学);Princeton University(普林斯顿大学);Rensselaer Polytechnic Institute(伦斯勒理工学院)