大模型对齐与安全

Gentopia: A Collaborative Platform for Tool-Augmented LLMs

Binfeng Xu, Xukun Liu, Hua Shen, Zeyu Han, Yuhan Li, Murong Yue, Zhiyuan Peng, Yuchen Liu, Ziyu Yao, Dongkuan Xu

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals

Susu Sun, Stefano Woerner, Andreas Maier, Lisa M. Koch, Christian F. Baumgartner

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Comments Accepted to MIDL 2023

KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering

Ankush Agarwal, Sakharam Gawade, Amar Prakash Azad, Pushpak Bhattacharyya

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection

Shuang Ao, Stefan Rueger, Advaith Siddharthan

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 7 pages

Journal ref 2023

Does Transliteration Help Multilingual Language Modeling?

Ibraheem Muhammad Moosa, Mahmud Elahi Akhter, Ashfia Binte Habib

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments In Findings of the Association for Computational Linguistics: EACL 2023

From OECD to India: Exploring cross-cultural differences in perceived trust, responsibility and reliance of AI and human experts

Vishakha Agrawal, Serhiy Kandul, Markus Kneer, Markus Christen

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CY

Advancing Visual Grounding with Scene Knowledge: Benchmark and Method

Zhihong Chen, Ruifei Zhang, Yibing Song, Xiang Wan, Guanbin Li

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Computer Vision and Natural Language Processing. 21 pages, 14 figures. CVPR-2023

Introducing Risk Shadowing For Decisive and Comfortable Behavior Planning

Tim Puphal, Julian Eggert

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Accepted at IEEE ITSC 2023

A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework

Gabriel Aguiar, Bartosz Krawczyk, Alberto Cano

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Journal ref Machine Learning, 2023

Android Malware Detection using Machine learning: A Review

Md Naseef-Ur-Rahman Chowdhury, Ahshanul Haque, Hamdy Soliman, Mohammad Sahinur Hossen, Tanjim Fatima, Imtiaz Ahmed

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 22 pages,2 figures, IntelliSys 2023

Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)

Mahum Naseer, Osman Hasan, Muhammad Shafique

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Distributionally Robust Deep Learning using Hardness Weighted Sampling

Lucas Fidon, Michael Aertsen, Thomas Deprest, Doaa Emam, Frédéric Guffens, Nada Mufti, Esther Van Elslander, Ernst Schwartz, Michael Ebner, Daniela Prayer, Gregor Kasprian, Anna L. David, Andrew Melbourne, Sébastien Ourselin, Jan Deprest, Georg Langs, Tom Vercauteren

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://www.melba-journal.org/papers/2022:019.html

Journal ref https://www.melba-journal.org/papers/2022:019.html

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Yasmine Karoui, Rémi Lebret, Negar Foroutan, Karl Aberer

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted to ACL 2023 as short paper

Evaluation of machine learning architectures on the quantification of epistemic and aleatoric uncertainties in complex dynamical systems

Stephen Guth, Alireza Mojahed, Themistoklis P. Sapsis

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Submitted for publication to "Computer Methods in Applied Mechanics and Engineering." 25 pages, 20 figures. arXiv admin note: text overlap with arXiv:1505.05424 by other authors

Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling

Fanyu Wang, Zhenping Xie

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted at ACL 2023, Findings

SAIL: Search-Augmented Instruction Learning

Hongyin Luo, Yung-Sung Chuang, Yuan Gong, Tianhua Zhang, Yoon Kim, Xixin Wu, Danny Fox, Helen Meng, James Glass

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL

Knowledge-Infused Self Attention Transformers

Kaushik Roy, Yuxin Zi, Vignesh Narayanan, Manas Gaur, Amit Sheth

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted for publication at the Second Workshop on Knowledge Augmented Methods for NLP, colocated with KDD 2023

Finding Competence Regions in Domain Generalization

Jens Müller, Stefan T. Radev, Robert Schmier, Felix Draxler, Carsten Rother, Ullrich Köthe

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Comments The paper has been published at TMLR (see https://openreview.net/forum?id=TSy0vuwQFN)

Journal ref Transactions on Machine Learning Research (06/2023)

Predicting Real-time Crash Risks during Hurricane Evacuation Using Connected Vehicle Data

Zaheen E Muktadi Syed, Samiul Hasan

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Maestro: A Gamified Platform for Teaching AI Robustness

Margarita Geleta, Jiacen Xu, Manikanta Loya, Junlin Wang, Sameer Singh, Zhou Li, Sergio Gago-Masague

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 9 pages, 6 figures, published at the Thirteenth Symposium on Educational Advances in Artificial Intelligence (EAAI-23) in the Association for the Advancement of Artificial Intelligence Conference (AAAI), 2023

AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment

Chunyi Li, Zicheng Zhang, Haoning Wu, Wei Sun, Xiongkuo Min, Xiaohong Liu, Guangtao Zhai, Weisi Lin

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI

Comments 12 pages, 11 figures

On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR

Tsz Kin Lam, Mayumi Ohta, Shigehiko Schamoni, Stefan Riezler

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted at INTERSPEECH 2021

Explainable AI via Learning to Optimize

Howard Heaton, Samy Wu Fung

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks

Haiyang Xu, Qinghao Ye, Xuan Wu, Ming Yan, Yuan Miao, Jiabo Ye, Guohai Xu, Anwen Hu, Yaya Shi, Guangwei Xu, Chenliang Li, Qi Qian, Maofei Que, Ji Zhang, Xiao Zeng, Fei Huang

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments Working in progress

Counterfactual Explanations and Predictive Models to Enhance Clinical Decision-Making in Schizophrenia using Digital Phenotyping

Juan Sebastian Canas, Francisco Gomez, Omar Costilla-Reyes

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI

Learning to Ground Instructional Articles in Videos through Narrations

Effrosyni Mavroudi, Triantafyllos Afouras, Lorenzo Torresani

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI

Comments 17 pages, 4 figures and 10 tables

ProgSG: Cross-Modality Representation Learning for Programs in Electronic Design Automation

Yunsheng Bai, Atefeh Sohrabizadeh, Zongyue Qin, Ziniu Hu, Yizhou Sun, Jason Cong

专题命中 安全评测 ：alignment(abstract)；分类 cs.LG

Comments Requires further polishing

Towards an Understanding and Explanation for Mixed-Initiative Artificial Scientific Text Detection

Luoxuan Weng, Minfeng Zhu, Kam Kwai Wong, Shi Liu, Jiashun Sun, Hang Zhu, Dongming Han, Wei Chen

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL

Explainable AI for Malnutrition Risk Prediction from m-Health and Clinical Data

Flavio Di Martino, Franca Delmastro, Cristina Dolciotti

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training

Linhao Dong, Zhecheng An, Peihao Wu, Jun Zhang, Lu Lu, Zejun Ma

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted by ACL 2023 Findings