大模型对齐与安全

Structuring a Training Strategy to Robustify Perception Models with Realistic Image Augmentations

Ahmed Hammam, Bharathwaj Krishnaswami Sreedhar, Nura Kawa, Tim Patzelt, Oliver De Candido

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Subgroup Analysis via Model-based Rule Forest

I-Ling Cheng, Chan Hsu, Chantung Ku, Pei-Ju Lee, Yihuang Kang

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

VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models

Wentao Wu, Fanghua Hong, Xiao Wang, Chenglong Li, Jin Tang

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

Comments In Peer Review

Tuning Language Models by Proxy

Alisa Liu, Xiaochuang Han, Yizhong Wang, Yulia Tsvetkov, Yejin Choi, Noah A. Smith

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments COLM 2024 camera-ready, code available at https://github.com/alisawuffles/proxy-tuning

Controllable Text Generation for Large Language Models: A Survey

Xun Liang, Hanyu Wang, Yezhaohui Wang, Shichao Song, Jiawei Yang, Simin Niu, Jie Hu, Dan Liu, Shunyu Yao, Feiyu Xiong, Zhiyu Li

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments 52 pages, 11 figures, 7 tables, 11 equations

A Comparative Analysis of Faithfulness Metrics and Humans in Citation Evaluation

Weijia Zhang, Mohammad Aliannejadi, Jiahuan Pei, Yifei Yuan, Jia-Hong Huang, Evangelos Kanoulas

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

Comments Accepted by the First Workshop on Large Language Model for Evaluation in Information Retrieval (LLM4Eval@SIGIR2024), non-archival. arXiv admin note: substantial text overlap with arXiv:2406.15264

Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks

Mehdi Heydari Shahna, Seyed Adel Alizadeh Kolagar, Jouni Mattila

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments This paper has been accepted at the International Conference on Mechatronics and Automation (ICMA 2024), sponsored by the IEEE

Research on the Application of Large Language Models in Automatic Question Generation: A Case Study of ChatGLM in the Context of High School Information Technology Curriculum

Yanxin Chen, Ling He

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

Applying and Evaluating Large Language Models in Mental Health Care: A Scoping Review of Human-Assessed Generative Tasks

Yining Hua, Hongbin Na, Zehan Li, Fenglin Liu, Xiao Fang, David Clifton, John Torous

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks

Jiaying Wu, Jiafeng Guo, Bryan Hooi

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

Comments Accepted to KDD 2024 (Research Track)

Addressing Distribution Shift in RTB Markets via Exponential Tilting

Minji Kim, Seong Jin Lee, Bumsik Kim

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

Assessing and Enhancing Large Language Models in Rare Disease Question-answering

Guanchu Wang, Junhao Ran, Ruixiang Tang, Chia-Yuan Chang, Chia-Yuan Chang, Yu-Neng Chuang, Zirui Liu, Vladimir Braverman, Zhandong Liu, Xia Hu

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

CoDefeater: Using LLMs To Find Defeaters in Assurance Cases

Usman Gohar, Michael C. Hunter, Robyn R. Lutz, Myra B. Cohen

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments ASE 2024 NIER

Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach

Shaun Ee, Joe O'Brien, Zoe Williams, Amanda El-Dakhakhni, Michael Aird, Alex Lintz

专题命中 安全评测 ：safety(abstract)；分类 cs.CY

Comments 79 pages

Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage

Aishwarya Gupta, Indranil Saha, Piyush Rai

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

Comments 20 pages (including references), 4 figures, 7 tables

Adaptive Data Quality Scoring Operations Framework using Drift-Aware Mechanism for Industrial Applications

Firas Bayram, Bestoun S. Ahmed, Erik Hallin

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

Comments 17 pages

Journal ref Journal of Systems and Software 2024

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

Stanislav Fort, Balaji Lakshminarayanan

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

Comments 34 pages, 25 figures, appendix

Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks

Gianluca De Stefano, Lea Schönherr, Giancarlo Pellegrino

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

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models

Wenqi Shao, Meng Lei, Yutao Hu, Peng Gao, Kaipeng Zhang, Fanqing Meng, Peng Xu, Siyuan Huang, Hongsheng Li, Yu Qiao, Ping Luo

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

Comments accepted to IEEE Transactions on Big Data. Project Page: http://lvlm-ehub.opengvlab.com/

PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models

Devansh Jain, Priyanshu Kumar, Samuel Gehman, Xuhui Zhou, Thomas Hartvigsen, Maarten Sap

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments Accepted to COLM 2024

DeVAn: Dense Video Annotation for Video-Language Models

Tingkai Liu, Yunzhe Tao, Haogeng Liu, Qihang Fan, Ding Zhou, Huaibo Huang, Ran He, Hongxia Yang

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

Comments Published in 62nd ACL (2024) Main Track

VisEval: A Benchmark for Data Visualization in the Era of Large Language Models

Nan Chen, Yuge Zhang, Jiahang Xu, Kan Ren, Yuqing Yang

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

CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liability

Gregory W. Kyro, Matthew T. Martin, Eric D. Watt, Victor S. Batista

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

A Chinese Dataset for Evaluating the Safeguards in Large Language Models

Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han, Lizhi Lin, Zhenxuan Zhang, Jingru Zhao, Preslav Nakov, Timothy Baldwin

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments 14 pages

Journal ref ACL2024-Findings

Being Accountable is Smart: Navigating the Technical and Regulatory Landscape of AI-based Services for Power Grid

Anna Volkova, Mahdieh Hatamian, Alina Anapyanova, Hermann de Meer

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Author's version of the paper for International Conference on Information Technology for Social Good (GoodIT '24), September 4--6, 2024, Bremen, Germany. It is posted here for your personal use. Not for redistribution

Journal ref In International Conference on Information Technology for Social Good (GoodIT '24), September 4--6, 2024, Bremen, Germany. ACM, New York, NY, USA, 9 pages

A SAT-based approach to rigorous verification of Bayesian networks

Ignacy Stępka, Nicholas Gisolfi, Artur Dubrawski

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Workshop on Explainable and Robust AI for Industry 4.0 & 5.0 (X-RAI) at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (2024)

Automated System-level Testing of Unmanned Aerial Systems

Hassan Sartaj, Asmar Muqeet, Muhammad Zohaib Iqbal, Muhammad Uzair Khan

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Published in Automated Software Engineering

Journal ref Autom Softw Eng 31, 64 (2024)

FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models

Huaiwen Zhang, Yu Chen, Ming Wang, Shi Feng

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

Comments Accepted to ICIC 2024

Journal ref Advanced Intelligent Computing Technology and Applications. ICIC 2024. Lecture Notes in Computer Science

Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations

Yongshuo Zong, Tingyang Yu, Ruchika Chavhan, Bingchen Zhao, Timothy Hospedales

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

Comments ICML 2024; v3 fix typo

RoCo:Robust Collaborative Perception By Iterative Object Matching and Pose Adjustment

Zhe Huang, Shuo Wang, Yongcai Wang, Wanting Li, Deying Li, Lei Wang

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

Comments ACM MM2024

Journal ref Proceedings of the 32nd ACM International Conference on Multimedia (MM '24), October 28-November 1, 2024, Melbourne, VIC, Australia