大模型对齐与安全 - arXivDaily 专题

2305.04547 2023-05-09 cs.CL 57%

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

专题命中 AI治理与伦理：safety(abstract)；分类 cs.CL

Comments Accepted by Findings of ACL 2023

2302.08001 2023-02-17 cs.AI cs.MA 57%

Learning Density-Based Correlated Equilibria for Markov Games

Libo Zhang, Yang Chen, Toru Takisaka, Bakh Khoussainov, Michael Witbrock, Jiamou Liu

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

2301.12566 2023-01-31 cs.CL cs.IR 57%

Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation

Zhiqi Huang, Puxuan Yu, James Allan

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL

2301.11737 2023-01-30 cs.LG 57%

Modeling human road crossing decisions as reward maximization with visual perception limitations

Yueyang Wang, Aravinda Ramakrishnan Srinivasan, Jussi P. P. Jokinen, Antti Oulasvirta, Gustav Markkula

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

Comments 6 pages, 5 figures,1 table, manuscript created for consideration at IEEE IV 2023 conference

2111.08094 2023-01-05 cs.CV cs.LG 57%

LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations

Weronika Hryniewska, Adrianna Grudzień, Przemysław Biecek

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

Journal ref Machine Learning (2022) 1-18

2112.06833 2022-11-30 cs.CY 57%

Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy

Peter Henderson, Ben Chugg, Brandon Anderson, Daniel E. Ho

专题命中 AI治理与伦理：safety(abstract)；分类 cs.CY

Comments Version 1 presented at Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice (2021), a NeurIPS 2021 Workshop; Version 2 presented at the 2nd ACM Symposium on Computer Science and Law (2022) (DOI: https://dl.acm.org/doi/10.1145/3511265.3550439)

2210.04491 2022-10-11 cs.LG stat.ML 57%

A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis

Laurent Risser, Agustin Picard, Lucas Hervier, Jean-Michel Loubes

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

2208.10087 2022-08-23 cs.CY 57%

A Trust Framework for Government Use of Artificial Intelligence and Automated Decision Making

Pia Andrews, Tim de Sousa, Bruce Haefele, Matt Beard, Marcus Wigan, Abhinav Palia, Kathy Reid, Saket Narayan, Morgan Dumitru, Alex Morrison, Geoff Mason, Aurelie Jacquet

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.CY

Comments Comments were integrated into the paper from all peer reviewers. Am happy to provide a copied history of comments if useful

2204.02725 2022-08-23 cs.IR cs.CL 57%

Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL

Comments Accepted by CIKM 2022

2208.08790 2022-08-19 cs.AI 57%

Explainable Reinforcement Learning on Financial Stock Trading using SHAP

Satyam Kumar, Mendhikar Vishal, Vadlamani Ravi

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

Comments 28 pages; 3 Tables; 21 Figures

2110.07120 2022-07-27 cs.LG cs.CV 57%

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Davis Brown, Henry Kvinge

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

Comments AdvML Frontiers 2022 @ ICML 2022 workshop

2206.00474 2022-06-02 cs.AI cs.HC 57%

Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness

Yuri Nakao, Lorenzo Strappelli, Simone Stumpf, Aisha Naseer, Daniele Regoli, Giulia Del Gamba

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.AI

Comments 44 pages, 17 figures, the draft of a paper on International Journal of Human-Computer Interaction

Journal ref International Journal of Human-Computer Interaction, 2022

2205.03824 2022-05-10 cs.AI 57%

A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges

Zhenghua Chen, Min Wu, Alvin Chan, Xiaoli Li, Yew-Soon Ong

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

2205.00656 2022-05-03 cs.CL 57%

Debiased Contrastive Learning of Unsupervised Sentence Representations

Kun Zhou, Beichen Zhang, Wayne Xin Zhao, Ji-Rong Wen

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL

Comments 11 pages, accepted by ACL 2022 main conference

2204.09622 2022-04-21 cs.HC cs.GL cs.LG 57%

A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning

Kory W. Mathewson, Patrick M. Pilarski

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

Comments 7 pages, 1 figure, Published at ML Evaluation Standards Workshop at ICLR 2022. arXiv admin note: substantial text overlap with arXiv:1905.06289

2008.06933 2022-04-05 cs.LG stat.ML 57%

The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line

Anna Bogomolova, Kseniia Kingsep, Boris Voskresenskii

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

Comments 8 pages, 6 figures

2111.02038 2022-03-23 cs.SE cs.LG 57%

Fair-SSL: Building fair ML Software with less data

Joymallya Chakraborty, Suvodeep Majumder, Huy Tu

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.LG

Journal ref International Workshop on Equitable Data and Technology (FairWare 2022 ), May 9, 2022, Pittsburgh, PA, USA

2203.09616 2022-03-21 astro-ph.CO cs.LG 57%

DeepLSS: breaking parameter degeneracies in large scale structure with deep learning analysis of combined probes

Tomasz Kacprzak, Janis Fluri

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.LG

Comments 18 pages, 10 figures, 2 tables, submitted to Physical Review

2112.01252 2022-03-11 cs.CY 57%

Australia's Approach to AI Governance in Security and Defence

Susannah Kate Devitt, Damian Copeland

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.CY

Comments 60 pages, 7 boxes, 2 figures, 2 annexes, submitted for Eds M. Raska, Z. Stanley-Lockman, & R. Bitzinger. AI Governance for National Security and Defence: Assessing Military AI Strategic Perspectives. Routledge

2202.11629 2022-02-24 cs.AI stat.ML 57%

A Complete Criterion for Value of Information in Soluble Influence Diagrams

Chris van Merwijk, Ryan Carey, Tom Everitt

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

Comments In Proceedings of the AAAI 2022 Conference

2111.15208 2022-02-04 cs.CV cs.AI 57%

HRNET: AI on Edge for mask detection and social distancing

Kinshuk Sengupta, Praveen Ranjan Srivastava

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

Journal ref SN Computer Science, 2022

2201.01659 2022-01-06 cs.CY 57%

From the Ground Truth Up: Doing AI Ethics from Practice to Principles

James Brusseau

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.CY

Journal ref AI & Soc (2022)

2012.15234 2022-01-05 cs.AI cs.GT 57%

Artificial Intelligence Development Races in Heterogeneous Settings

Theodor Cimpeanu, Francisco C. Santos, Luis Moniz Pereira, Tom Lenaerts, The Anh Han

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

Comments 42 pages, 13 figures, accepted for publication in Nature Scientific Reports

2112.06883 2021-12-14 cs.SE cs.AI cs.DC 57%

A Methodology for a Scalable, Collaborative, and Resource-Efficient Platform to Facilitate Healthcare AI Research

Raphael Y. Cohen, Vesela P. Kovacheva

专题命中 AI治理与伦理：safety(abstract)；分类 cs.AI

2106.16122 2021-11-03 cs.HC cs.CY 57%

Zombies in the Loop? Humans Trust Untrustworthy AI-Advisors for Ethical Decisions

Sebastian Krügel, Andreas Ostermaier, Matthias Uhl

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.CY

2110.05164 2021-10-12 cs.CY 57%

Ethical Assurance: A practical approach to the responsible design, development, and deployment of data-driven technologies

Christopher Burr, David Leslie

专题命中 AI治理与伦理：safety(abstract)；分类 cs.CY

2101.00421 2021-09-22 cs.CL 57%

The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation

Nikolay Bogoychev, Pinzhen Chen

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL

Comments Accepted at Workshop on Insights from Negative Results in NLP 2021

2109.05388 2021-09-14 cs.CL 57%

The Impact of Positional Encodings on Multilingual Compression

Vinit Ravishankar, Anders Søgaard

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL

2107.14099 2021-07-30 cs.CY 57%

The ghost of AI governance past, present and future: AI governance in the European Union

Charlotte Stix

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.CY

2107.13076 2021-07-29 cs.HC cs.LG 57%

Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI

ennifer Chubba, Sondess Missaouib, Shauna Concannonc, Liam Maloneyb, James Alfred Walker

专题命中 AI治理与伦理：safety(abstract)；分类 cs.LG

1. AI治理与伦理 1836 篇

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

Learning Density-Based Correlated Equilibria for Markov Games

Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation

Modeling human road crossing decisions as reward maximization with visual perception limitations

LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations

Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy

A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis

A Trust Framework for Government Use of Artificial Intelligence and Automated Decision Making

Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning

Explainable Reinforcement Learning on Financial Stock Trading using SHAP

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness

A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges

Debiased Contrastive Learning of Unsupervised Sentence Representations

A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning

The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line

Fair-SSL: Building fair ML Software with less data

DeepLSS: breaking parameter degeneracies in large scale structure with deep learning analysis of combined probes

Australia's Approach to AI Governance in Security and Defence

A Complete Criterion for Value of Information in Soluble Influence Diagrams

HRNET: AI on Edge for mask detection and social distancing

From the Ground Truth Up: Doing AI Ethics from Practice to Principles

Artificial Intelligence Development Races in Heterogeneous Settings

A Methodology for a Scalable, Collaborative, and Resource-Efficient Platform to Facilitate Healthcare AI Research

Zombies in the Loop? Humans Trust Untrustworthy AI-Advisors for Ethical Decisions

Ethical Assurance: A practical approach to the responsible design, development, and deployment of data-driven technologies

The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation

The Impact of Positional Encodings on Multilingual Compression

The ghost of AI governance past, present and future: AI governance in the European Union

Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI