大模型对齐与安全

Deciphering Diagnoses: How Large Language Models Explanations Influence Clinical Decision Making

D. Umerenkov, G. Zubkova, A. Nesterov

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Wenhu Chen, Hexiang Hu, Yandong Li, Nataniel Ruiz, Xuhui Jia, Ming-Wei Chang, William W. Cohen

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

Comments Accepted at NeurIPS 2023. Model Service to be appear as Google Vertex AI - Instant Tuning (https://cloud.google.com/vertex-ai/docs/generative-ai/image/fine-tune-model). The link to demo video: https://www.youtube.com/watch?v=Q2xQ91D_dhM&t=2071s&ab_channel=GoogleCloud

Coordinated pausing: An evaluation-based coordination scheme for frontier AI developers

Jide Alaga, Jonas Schuett

专题命中 安全评测 ：safety(abstract)；分类 cs.CY

Comments 24 pages, 3 figures, 1 table

The Devil is in the Details: A Deep Dive into the Rabbit Hole of Data Filtering

Haichao Yu, Yu Tian, Sateesh Kumar, Linjie Yang, Heng Wang

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

Comments 12 pages, 10 figures

Perception for Humanoid Robots

Arindam Roychoudhury, Shahram Khorshidi, Subham Agrawal, Maren Bennewitz

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 20 pages, 4 figures. To be published in Current Robotics Reports (Springer Nature)

SLHCat: Mapping Wikipedia Categories and Lists to DBpedia by Leveraging Semantic, Lexical, and Hierarchical Features

Zhaoyi Wang, Zhenyang Zhang, Jiaxin Qin, Mizuho Iwaihara

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

Comments ICADL23

Capture Agent Free Biosensing using Porous Silicon Arrays and Machine Learning

Simon J. Ward, Tengfei Cao, Xiang Zhou, Catie Chang, Sharon M. Weiss

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments 15 pages, 3 figures, 2 tables

Journal ref Biosensors 13 (2023) 1-12

Model evaluation for extreme risks

Toby Shevlane, Sebastian Farquhar, Ben Garfinkel, Mary Phuong, Jess Whittlestone, Jade Leung, Daniel Kokotajlo, Nahema Marchal, Markus Anderljung, Noam Kolt, Lewis Ho, Divya Siddarth, Shahar Avin, Will Hawkins, Been Kim, Iason Gabriel, Vijay Bolina, Jack Clark, Yoshua Bengio, Paul Christiano, Allan Dafoe

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

Comments Fixed typos; added citation

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

Zeyu Lu, Di Huang, Lei Bai, Jingjing Qu, Chengyue Wu, Xihui Liu, Wanli Ouyang

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

Trusta: Reasoning about Assurance Cases with Formal Methods and Large Language Models

Zezhong Chen, Yuxin Deng, Wenjie Du

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 38 pages

Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models

Levon Haroutunian, Zhuang Li, Lucian Galescu, Philip Cohen, Raj Tumuluri, Gholamreza Haffari

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

Comments IJCNLP-AACL 2023

ContextRef: Evaluating Referenceless Metrics For Image Description Generation

Elisa Kreiss, Eric Zelikman, Christopher Potts, Nick Haber

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

Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer Grading

Gerd Kortemeyer

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

Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models

Cheng Chen, Lei Fan

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Stochastic Environmental Research and Risk Assessment

Journal ref Stochastic Environmental Research and Risk Assessment, 13 September 2023

GPU-Accelerated Verification of Machine Learning Models for Power Systems

Samuel Chevalier, Ilgiz Murzakhanov, Spyros Chatzivasileiadis

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, Timothy Baldwin

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments 18 pages, 9 figures, 11 tables

Detecting Evidence of Organization in groups by Trajectories

T. F. Silva, J. E. B. Maia

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 17 pages, 16 figures, 3 algorithms, 1 table

Benchmarking Robustness of AI-Enabled Multi-sensor Fusion Systems: Challenges and Opportunities

Xinyu Gao, Zhijie Wang, Yang Feng, Lei Ma, Zhenyu Chen, Baowen Xu

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments To appear in ESEC/FSE 2023

Meaningful XAI Based on User-Centric Design Methodology

Winston Maxwell, Bruno Dumas

专题命中 安全评测 ：safety(abstract)；分类 cs.CY

Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation

Kevin Krahn, Derrick Tate, Andrew C. Lamicela

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

Comments Paper accepted for publication at the First Workshop on Ancient Language Processing (ALP) 2023; 10 pages, 3 figures, 9 tables

Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving

Lin-Chi Wu, Zengjie Zhang, Sofie Haesaert, Zhiqiang Ma, Zhiyong Sun

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Interpretable machine learning-accelerated seed treatment by nanomaterials for environmental stress alleviation

Hengjie Yu, Dan Luo, Sam F. Y. Li, Maozhen Qu, Da Liu, Yingchao He, Fang Cheng

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

Comments 30 pages, 6 figures

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

Bo Dai, Linge Wang, Baoxiong Jia, Zeyu Zhang, Song-Chun Zhu, Chi Zhang, Yixin Zhu

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

Comments 19 pages, 16 figures, selected for an Oral presentation at ICCV 2023. Project link: https://pku.ai/publication/intuitive2023iccv/

An Empirical Study of AI-based Smart Contract Creation

Rabimba Karanjai, Edward Li, Lei Xu, Weidong Shi

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Updated to address issues

Physics Informed Recurrent Neural Networks for Seismic Response Evaluation of Nonlinear Systems

Faisal Nissar Malik, James Ricles, Masoud Yari, Malik Arsala Nissar

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Undersampling and Cumulative Class Re-decision Methods to Improve Detection of Agitation in People with Dementia

Zhidong Meng, Andrea Iaboni, Bing Ye, Kristine Newman, Alex Mihailidis, Zhihong Deng, Shehroz S. Khan

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments 19 pages, 6 figures

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

Robin Hesse, Simone Schaub-Meyer, Stefan Roth

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Accepted at ICCV 2023. Code: https://github.com/visinf/funnybirds

Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Methods Integrated in Instrumentation & Control Systems

Edward Chen, Han Bao, Nam Dinh

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments This paper was originally presented at the 13th Nuclear Plant Instrumentation, Control & Human-Machine Interface Technologies conference and was awarded best student paper

A Feature Set of Small Size for the PDF Malware Detection

Ran Liu, Charles Nicholas

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

Comments Accepted for publication at the ACM SIGKDD & Annual KDD Conference workshop on Knowledge-infused Machine Learning, 2023

Yggdrasil Decision Forests: A Fast and Extensible Decision Forests Library

Mathieu Guillame-Bert, Sebastian Bruch, Richard Stotz, Jan Pfeifer

专题命中 安全评测 ：safety(abstract)；分类 cs.LG