大模型对齐与安全

MedISure: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysis

Adam Byfield, William Poulett, Ben Wallace, Anusha Jose, Shatakshi Tyagi, Smita Shembekar, Adnan Qayyum, Junaid Qadir, Muhammad Bilal

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Orca 2: Teaching Small Language Models How to Reason

Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes, Sahaj Agarwal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah

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

Comments Added url to model weights fixed typo in Author name

Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space

Xuan Zhao, Klaus Broelemann, Gjergji Kasneci

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

Comments XAI workshop of IJCAI 2023

Digital Twin Framework for Optimal and Autonomous Decision-Making in Cyber-Physical Systems: Enhancing Reliability and Adaptability in the Oil and Gas Industry

Carine Menezes Rebello, Johannes Jäschkea, Idelfonso B. R. Nogueira

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

AI-Augmented Business Process Management Systems: A Research Manifesto

Marlon Dumas, Fabiana Fournier, Lior Limonad, Andrea Marrella, Marco Montali, Jana-Rebecca Rehse, Rafael Accorsi, Diego Calvanese, Giuseppe De Giacomo, Dirk Fahland, Avigdor Gal, Marcello La Rosa, Hagen Völzer, Ingo Weber

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

Comments 19 pages, 1 figure

Journal ref ACM Transactions on Management Information Systems, 31 January 2023 Volume 14, Issue 1, Article No.: 11, pp 1-19

Western, Religious or Spiritual: An Evaluation of Moral Justification in Large Language Models

Eyup Engin Kucuk, Muhammed Yusuf Kocyigit

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

Comments 16 pages total, 8 pages main paper

A Saliency-based Clustering Framework for Identifying Aberrant Predictions

Aina Tersol Montserrat, Alexander R. Loftus, Yael Daihes

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

STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training

Weihong Zhong, Mao Zheng, Duyu Tang, Xuan Luo, Heng Gong, Xiaocheng Feng, Bing Qin

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

Comments AAAI 2023, 7 pages, 3 figures

OLaLa: Ontology Matching with Large Language Models

Sven Hertling, Heiko Paulheim

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

Comments Accepted at K-CAP 2023 conference

GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks

Xinlu Zhang, Yujie Lu, Weizhi Wang, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, Linda Ruth Petzold

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

Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning

Junyu Lu, Dixiang Zhang, Xiaojun Wu, Xinyu Gao, Ruyi Gan, Jiaxing Zhang, Yan Song, Pingjian Zhang

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

Investigative Pattern Detection Framework for Counterterrorism

Shashika R. Muramudalige, Benjamin W. K. Hung, Rosanne Libretti, Jytte Klausen, Anura P. Jayasumana

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments 9 pages, 4 figures

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

Xinyu She, Yue Liu, Yanjie Zhao, Yiling He, Li Li, Chakkrit Tantithamthavorn, Zhan Qin, Haoyu Wang

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

Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving

Hongkuan Zhou, Aifen Sui, Letian Shi, Yinxian Li

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Evaluating Verifiability in Generative Search Engines

Nelson F. Liu, Tianyi Zhang, Percy Liang

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

Comments 25 pages, 12 figures; to appear in Findings of EMNLP 2023

Establishing Trustworthiness: Rethinking Tasks and Model Evaluation

Robert Litschko, Max Müller-Eberstein, Rob van der Goot, Leon Weber, Barbara Plank

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

Comments Accepted at EMNLP 2023 (Main Conference), camera-ready

Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

Andrea Sottana, Bin Liang, Kai Zou, Zheng Yuan

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

Comments Accepted at EMNLP 2023

Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications

Jiangwei Wang, Shuo Yang, Ziyan An, Songyang Han, Zhili Zhang, Rahul Mangharam, Meiyi Ma, Fei Miao

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models

Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre, Ai Ti Aw, Nancy F. Chen

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

Comments EMNLP 2023 (Main, Long paper)

Paxion: Patching Action Knowledge in Video-Language Foundation Models

Zhenhailong Wang, Ansel Blume, Sha Li, Genglin Liu, Jaemin Cho, Zineng Tang, Mohit Bansal, Heng Ji

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

Comments NeurIPS 2023 spotlight

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Heng Huang, Jiuxiang Gu, Tianyi Zhou

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

Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness

Shide Du, Zihan Fang, Shiyang Lan, Yanchao Tan, Manuel Günther, Shiping Wang, Wenzhong Guo

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

A Machine Learning-based Algorithm for Automated Detection of Frequency-based Events in Recorded Time Series of Sensor Data

Bahareh Medghalchi, Andreas Vogel

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness

Peiyu Xiong, Michael Tegegn, Jaskeerat Singh Sarin, Shubhraneel Pal, Julia Rubin

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Accepted to ACM Computing Surveys, 40 pages, 24 figures

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

Xiao Wang, Yuansen Zhang, Tianze Chen, Songyang Gao, Senjie Jin, Xianjun Yang, Zhiheng Xi, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xuanjing Huang

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Extrapolating Large Language Models to Non-English by Aligning Languages

Wenhao Zhu, Yunzhe Lv, Qingxiu Dong, Fei Yuan, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

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

Do Large Language Models Know about Facts?

Xuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, Philip S. Yu, Zhijiang Guo

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

Comments 20 pages, 8 figures

Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics

Jan N. Fuhg, Reese E. Jones, Nikolaos Bouklas

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

Comments 34 pages, 19 Figures

Investigating the Limitation of CLIP Models: The Worst-Performing Categories

Jie-Jing Shao, Jiang-Xin Shi, Xiao-Wen Yang, Lan-Zhe Guo, Yu-Feng Li

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

PyTrial: Machine Learning Software and Benchmark for Clinical Trial Applications

Zifeng Wang, Brandon Theodorou, Tianfan Fu, Cao Xiao, Jimeng Sun

专题命中 安全评测 ：safety(abstract)；分类 cs.AI