大模型对齐与安全

Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios

Sabit Hassan, Anthony Sicilia, Malihe Alikhani

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL

Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression

Zhichao Xu, Ashim Gupta, Tao Li, Oliver Bentham, Vivek Srikumar

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL

Comments Findings of EMNLP 2024

Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective

Taelin Karidi, Eitan Grossman, Omri Abend

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

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju

专题命中 安全评测 ：safety(title,abstract)；分类 cs.AI

SoK: Towards Security and Safety of Edge AI

Tatjana Wingarz, Anne Lauscher, Janick Edinger, Dominik Kaaser, Stefan Schulte, Mathias Fischer

专题命中 安全评测 ：safety(title,abstract)；分类 cs.AI

Learning Personalized Alignment for Evaluating Open-ended Text Generation

Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian

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

Comments 19 pages

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation

KaShun Shum, Minrui Xu, Jianshu Zhang, Zixin Chen, Shizhe Diao, Hanze Dong, Jipeng Zhang, Muhammad Omer Raza

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

Comments EMNLP 2024

Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement

Yunlong Feng, Dechuan Teng, Yang Xu, Honglin Mu, Xiao Xu, Libo Qin, Qingfu Zhu, Wanxiang Che

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

Comments EMNLP 2024 Findings

Towards Bridging the FL Performance-Explainability Trade-Off: A Trustworthy 6G RAN Slicing Use-Case

Swastika Roy, Hatim Chergui, Christos Verikoukis

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

Comments Submitted for possible publication in IEEE. arXiv admin note: text overlap with arXiv:2210.10147

Interactive AI Alignment: Specification, Process, and Evaluation Alignment

Michael Terry, Chinmay Kulkarni, Martin Wattenberg, Lucas Dixon, Meredith Ringel Morris

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

Self-Judge: Selective Instruction Following with Alignment Self-Evaluation

Hai Ye, Hwee Tou Ng

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

Comments Under review

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

Yun-Da Tsai, Ting-Yu Yen, Keng-Te Liao, Shou-De Lin

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

Comments arXiv admin note: text overlap with arXiv:2407.05036

Overcoming Imbalanced Safety Data Using Extended Accident Triangle

Kailai Sun, Tianxiang Lan, Yang Miang Goh, Yueng-Hsiang Huang

专题命中 安全评测 ：safety(title,abstract)；分类 cs.LG

SAFETY-J: Evaluating Safety with Critique

Yixiu Liu, Yuxiang Zheng, Shijie Xia, Jiajun Li, Yi Tu, Chaoling Song, Pengfei Liu

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL

CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagery

Thomas Manzini, Priyankari Perali, Raisa Karnik, Robin Murphy

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

Comments 16 Pages, 7 Figures, 6 Tables

Navigating the EU AI Act: A Methodological Approach to Compliance for Safety-critical Products

J. Kelly, S. Zafar, L. Heidemann, J. Zacchi, D. Espinoza, N. Mata

专题命中 安全评测 ：safety(title,abstract)；分类 cs.AI

Comments To be published in: 2024 IEEE Conference on Artificial Intelligence (CAI 2024)

DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment

Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee

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

Comments Accepted to Interspeech 2024

Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment

Paarth Neekhara, Shehzeen Hussain, Subhankar Ghosh, Jason Li, Rafael Valle, Rohan Badlani, Boris Ginsburg

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

Comments Published as a conference paper at INTERSPEECH 2024

SafetyBench: Evaluating the Safety of Large Language Models

Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, Minlie Huang

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL

Comments ACL 2024 Main Conference

Trustworthy Artificial Intelligence in the Context of Metrology

Tameem Adel, Sam Bilson, Mark Levene, Andrew Thompson

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

Journal ref In Producing Artificial Intelligent Systems: The roles of Benchmarking, Standardisation and Certification, Studies in Computational Intelligence, edited by M. I. A. Ferreira, 2024, Springer

VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment

Bing Han, Long Zhou, Shujie Liu, Sanyuan Chen, Lingwei Meng, Yanming Qian, Yanqing Liu, Sheng Zhao, Jinyu Li, Furu Wei

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

Comments 15 pages, 5 figures

Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3

James Derek Lomas, Willem van der Maden, Sohhom Bandyopadhyay, Giovanni Lion, Nirmal Patel, Gyanesh Jain, Yanna Litowsky, Haian Xue, Pieter Desmet

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

TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection

Hui Liu, Wenya Wang, Haoru Li, Haoliang Li

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

Comments Accepted by Findings of ACL 2024. 28 pages, 2 figures, 16 tables

Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence

José Daniel Pascual-Triana, Alberto Fernández, Javier Del Ser, Francisco Herrera

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

Comments 21 pages, 6 figures. Submitted to Information Sciences

Developing trustworthy AI applications with foundation models

Michael Mock, Sebastian Schmidt, Felix Müller, Rebekka Görge, Anna Schmitz, Elena Haedecke, Angelika Voss, Dirk Hecker, Maximillian Poretschkin

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

Comments 24 pages, 11 figures

Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life

Kazuma Kobayashi, Syed Bahauddin Alam

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

Journal ref Engineering Applications of Artificial Intelligence 129 (2024): 107620

Lessons Learned in Performing a Trustworthy AI and Fundamental Rights Assessment

Marjolein Boonstra, Frédérick Bruneault, Subrata Chakraborty, Tjitske Faber, Alessio Gallucci, Eleanore Hickman, Gerard Kema, Heejin Kim, Jaap Kooiker, Elisabeth Hildt, Annegret Lamadé, Emilie Wiinblad Mathez, Florian Möslein, Genien Pathuis, Giovanni Sartor, Marijke Steege, Alice Stocco, Willy Tadema, Jarno Tuimala, Isabel van Vledder, Dennis Vetter, Jana Vetter, Magnus Westerlund, Roberto V. Zicari

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

Comments On behalf of the Z-Inspection$^{\small{\circledR}}$ Initiative

Hyperbolic Delaunay Geometric Alignment

Aniss Aiman Medbouhi, Giovanni Luca Marchetti, Vladislav Polianskii, Alexander Kravberg, Petra Poklukar, Anastasia Varava, Danica Kragic

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

PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination

Anant Khandelwal

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

Comments Accepted at CVPR 2024 LIMIT, 12 pages, 8 Tables, 2 Figures

Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects

Junyu Lu, Dixiang Zhang, Songxin Zhang, Zejian Xie, Zhuoyang Song, Cong Lin, Jiaxing Zhang, Bingyi Jing, Pingjian Zhang

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