大模型对齐与安全 - arXivDaily 专题

1905.01320 2019-05-07 cs.LG cs.AI stat.ML 62%

Meta-learners' learning dynamics are unlike learners'

Neil C. Rabinowitz

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

Comments 26 pages, 23 figures

1812.05659 2019-02-21 cs.CV cs.AI cs.HC cs.LG 62%

Artificial Intelligence Assisted Infrastructure Assessment Using Mixed Reality Systems

Enes Karaaslan, Ulas Bagci, F. Necati Catbas

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

Comments 5,240 word texts, 3 tables, 14 figures. Transportation Research Record: Journal of the Transportation Research Board, 2019

1812.01813 2018-12-06 cs.CY cs.LG 62%

Machine-learned epidemiology: real-time detection of foodborne illness at scale

Adam Sadilek, Stephanie Caty, Lauren DiPrete, Raed Mansour, Tom Schenk, Mark Bergtholdt, Ashish Jha, Prem Ramaswami, Evgeniy Gabrilovich

专题命中其他安全：safety(abstract)；分类 cs.CY、cs.LG

Journal ref npj Digital Medicine 1:36 (2018)

1703.10284 2018-11-28 cs.AI cs.LG 62%

Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization

Mark O. Riedl, Brent Harrison

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

Comments 6 pages; 1 figure; title, abstract updated; new experimental results

Journal ref Proceedings of the AAAI 2019 Workshop on SafeAI

1807.04587 2018-11-21 cs.LG cs.AI cs.NE stat.ML 62%

Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

Sergey Bartunov, Adam Santoro, Blake A. Richards, Luke Marris, Geoffrey E. Hinton, Timothy Lillicrap

专题命中其他安全：alignment(abstract)；分类 cs.AI、cs.LG

Comments NIPS 2018. Version 2 contains more experimental data including best hyperparameters found

1811.05544 2018-11-15 cs.CL cs.LG stat.ML 62%

An Introductory Survey on Attention Mechanisms in NLP Problems

Dichao Hu

专题命中其他安全：alignment(abstract)；分类 cs.CL、cs.LG

Comments 9 pages

1810.02724 2018-10-08 cs.GL cs.AI cs.CY 62%

Human Indignity: From Legal AI Personhood to Selfish Memes

Roman V. Yampolskiy

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.CY

1810.01989 2018-10-05 cs.AI cs.LG 62%

Verification for Machine Learning, Autonomy, and Neural Networks Survey

Weiming Xiang, Patrick Musau, Ayana A. Wild, Diego Manzanas Lopez, Nathaniel Hamilton, Xiaodong Yang, Joel Rosenfeld, Taylor T. Johnson

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

1808.07899 2018-08-27 cs.AI cs.CY 62%

A Century Long Commitment to Assessing Artificial Intelligence and its Impact on Society

Barbara J. Grosz, Peter Stone

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.CY

Comments This paper will appear in Communications of the ACM (December 2018, vol 61, no. 12)

1805.09938 2018-05-28 cs.AI cs.LG 62%

Automated Verification of Neural Networks: Advances, Challenges and Perspectives

Francesco Leofante, Nina Narodytska, Luca Pulina, Armando Tacchella

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

1805.00900 2018-05-03 cs.AI cs.CL cs.CV cs.IR 62%

Images & Recipes: Retrieval in the cooking context

Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Matthieu Cord

专题命中其他安全：alignment(abstract)；分类 cs.CL、cs.AI

Comments Published at DECOR / ICDE 2018. Extended version accepted at SIGIR 2018, available here: arXiv:1804.11146

1802.01096 2018-02-09 cs.SE cs.AI cs.HC cs.LG cs.NE 62%

Software Engineers vs. Machine Learning Algorithms: An Empirical Study Assessing Performance and Reuse Tasks

Nathalia Nascimento, Carlos Lucena, Paulo Alencar, Donald Cowan

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

Comments 22 pages. To be submitted to IEEE Transactions on Software Engineering

1712.01996 2017-12-07 eess.AS cs.AI cs.CL cs.SD 62%

An analysis of incorporating an external language model into a sequence-to-sequence model

Anjuli Kannan, Yonghui Wu, Patrick Nguyen, Tara N. Sainath, Zhifeng Chen, Rohit Prabhavalkar

专题命中其他安全：alignment(abstract)；分类 cs.CL、cs.AI

1512.00177 2017-09-25 cs.CL cs.AI cs.NE 62%

LSTM Neural Reordering Feature for Statistical Machine Translation

Yiming Cui, Shijin Wang, Jianfeng Li

专题命中其他安全：alignment(abstract)；分类 cs.CL、cs.AI

Comments 6 pages, accepted by NAACL2016 short paper

1605.08535 2017-07-17 cs.SE cs.CL cs.LG cs.NE 62%

Deep API Learning

Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim

专题命中其他安全：alignment(abstract)；分类 cs.CL、cs.LG

Comments The paper is accepted at FSE 2016 (the 24th ACM SIGSOFT International Symposium on the Foundations of Software Engineering)

1612.01086 2017-03-28 cs.AI cs.LG cs.RO 62%

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision

Bar Hilleli, Ran El-Yaniv

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

1401.3427 2014-01-16 cs.LG cs.AI 62%

Analogical Dissimilarity: Definition, Algorithms and Two Experiments in Machine Learning

Laurent Miclet, Sabri Bayoudh, Arnaud Delhay

专题命中其他安全：alignment(abstract)；分类 cs.AI、cs.LG

Journal ref Journal Of Artificial Intelligence Research, Volume 32, pages 793-824, 2008

2606.13254 2026-06-12 cs.CL 新提交 61%

Evaluating Pluralism in LLMs through Latent Perspectives

通过潜在视角评估LLM中的多元主义

Laura Majer, Jan Šnajder, Martin Tutek

机构 * University of Helsinki（赫尔辛基大学）； ETH Zurich（苏黎世联邦理工学院）

专题命中其他安全：alignment(abstract,comments)；分类 cs.CL

AI总结提出一种领域无关的多层无监督框架，从LLM生成文本中提取潜在视角，评估多元主义差距，发现稀有视角仍被不成比例地低估。

Comments Pluralistic Alignment Workshop @ ICML 2026

2508.10515 2026-03-23 physics.comp-ph cs.CE cs.LG cs.SY eess.SY 61%

Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT Modules

IGBT模块焊层退化与温度监测的虚拟传感

Andrea Urgolo, Monika Stipsitz, Hèlios Sanchis-Alepuz

机构 * Silicon Austria Labs GmbH（硅 Austria 实验室）

专题命中其他安全：safety(abstract,journal_ref)；分类 cs.LG

AI总结本文利用机器学习虚拟传感技术，通过有限物理传感器估计IGBT模块焊层退化状态及温度分布，实现高精度退化区域估计和表面温度复现。

Comments Andrea Urgolo and Monika Stipsitz contributed equally to this work

Journal ref 2025 9th International Conference on System Reliability and Safety (ICSRS), Turin, Italy, 2025, pp. 538-547

2603.09020 2026-03-11 cs.HC cs.AI 61%

AI Phenomenology for Understanding Human-AI Experiences Across Eras

人工智能现象学：理解跨时代的以人为本的AI体验

Bhada Yun, Evgenia Taranova, Dana Feng, Renn Su, April Yi Wang

机构 * ETH Zürich（苏黎世联邦理工学院）； University of Bergen（卑尔根大学）； Stanford University（斯坦福大学）

专题命中其他安全：alignment(abstract,comments)；分类 cs.AI

AI总结本文提出人工智能现象学，通过研究用户与AI交互的主观体验，促进双向人机对齐，并提供可重复的方法论工具。

Comments This is an accepted workshop paper at CHI '26, "W37: Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures", or https://bialign-workshop.github.io/2026/cfp

2603.03074 2026-03-04 cs.HC cs.AI 61%

Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice

为实践者设计生成式AI：探索与创意实践对齐的交互方法

Xiaohan Peng, Wendy E. Mackay, Janin Koch

机构 * LISN Université Paris-Saclay, CNRS, Inria（LISN 巴黎-萨克雷大学，法国国家科学研究中心，法国国家信息与自动化技术研究所）； UMR 9189 CRIStAL Univ. Lille, Inria, CNRS, Centrale Lille（UMR 9189 CRIStAL 利摩日大学，法国国家信息与自动化技术研究所，法国国家科学研究中心，利摩日中央理工大学）

专题命中其他安全：alignment(abstract,comments)；分类 cs.AI

AI总结本文提出三种交互方法，帮助设计师在不同阶段引导生成式AI与创意实践对齐，强调动态协商与主动/被动角色的适应性。

Comments Accepted to ACM CHI 2026 Workshop on Bidirectional Human-AI Alignment

2510.18745 2025-10-22 cs.CL 61%

Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting

Taha Binhuraib, Greta Tuckute, Nicholas Blauch

机构 * Novus Technologies ； MIT（麻省理工学院）； Harvard University（哈佛大学）

专题命中其他安全：alignment(abstract,comments)；分类 cs.CL

Comments ICLR 2024 Workshop on Representational Alignment (Re-Align) Camera Ready

2506.14390 2025-06-18 cs.LG cs.CV 61%

Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection

Conrad Orglmeister, Erik Bochinski, Volker Eiselein, Elvira Fleig

机构 * Digitale Schiene Deutschland, DB InfraGO AG（Digitale Schiene Deutschland，DB InfraGO AG）； Communication Systems Group, Technische Universität Berlin（通信系统组，技术大学柏林）

专题命中其他安全：safety(abstract,comments)；分类 cs.LG

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in Computer Safety, Reliability and Security - SAFECOMP 2024 Workshops - DECSoS, SASSUR, TOASTS, and WAISE, and is available online at https://doi.org/10.1007/978-3-031-68738-9_29

2503.11096 2025-03-17 cs.CV cs.AI cs.HC 61%

Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation

He Zhang, Xinyi Fu, John M. Carroll

专题命中其他安全：alignment(abstract,comments)；分类 cs.AI

Comments This paper will appear at ICLR 2025 Workshop on Bidirectional Human-AI Alignment

2502.14095 2025-02-21 cs.CL 61%

Retrieving Versus Understanding Extractive Evidence in Few-Shot Learning

Karl Elbakian, Samuel Carton

专题命中其他安全：alignment(abstract,comments)；分类 cs.CL

Comments 9 pages, 8 figures, Accepted to AAAI 2025 Main Conference (AI Alignment Track)

2403.06204 2024-03-12 cs.CL 61%

Identifying and interpreting non-aligned human conceptual representations using language modeling

Wanqian Bao, Uri Hasson

专题命中其他安全：alignment(abstract,comments)；分类 cs.CL

Comments To appear at the ICLR 2024 Workshop on Representational Alignment (Re-Align)

2301.08138 2023-01-20 cs.SE cs.AI cs.SY eess.SY 61%

Architecting Safer Autonomous Aviation Systems

Jane Fenn, Mark Nicholson, Ganesh Pai, Michael Wilkinson

专题命中其他安全：safety(abstract,comments)；分类 cs.AI

Comments 18 pages, 12 figures, to appear in the proceedings of the 2023 Safety-critical Systems Symposium (SSS '23), York, UK

2210.09959 2022-10-19 cs.LG 61%

Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder

Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran

专题命中其他安全：safety(abstract,comments)；分类 cs.LG

Comments Accepted in The 6th International Conference on System Reliability and Safety (ICSRS) 2022

2202.12991 2022-03-01 cs.AI cs.CR 61%

Attacks and Faults Injection in Self-Driving Agents on the Carla Simulator -- Experience Report

Niccolò Piazzesi, Massimo Hong, Andrea Ceccarelli

专题命中其他安全：safety(abstract,comments)；分类 cs.AI

Comments submitted version; appeared at: International Conference on Computer Safety, Reliability, and Security. Springer, Cham, 2021

2003.00431 2020-03-03 cs.AI 61%

A Study on Multimodal and Interactive Explanations for Visual Question Answering

Kamran Alipour, Jurgen P. Schulze, Yi Yao, Avi Ziskind, Giedrius Burachas

专题命中其他安全：safety(abstract,journal_ref)；分类 cs.AI

Comments http://ceur-ws.org/Vol-2560/paper44.pdf

Journal ref Proceedings of the Workshop on Artificial Intelligence Safety (SafeAI 2020) co-located with 34th AAAI Conference on Artificial Intelligence (AAAI 2020), New York, USA, Feb 7, 2020

1. 其他安全 8057 篇

Meta-learners' learning dynamics are unlike learners'

Artificial Intelligence Assisted Infrastructure Assessment Using Mixed Reality Systems

Machine-learned epidemiology: real-time detection of foodborne illness at scale

Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization

Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

An Introductory Survey on Attention Mechanisms in NLP Problems

Human Indignity: From Legal AI Personhood to Selfish Memes

Verification for Machine Learning, Autonomy, and Neural Networks Survey

A Century Long Commitment to Assessing Artificial Intelligence and its Impact on Society

Automated Verification of Neural Networks: Advances, Challenges and Perspectives

Images & Recipes: Retrieval in the cooking context

Software Engineers vs. Machine Learning Algorithms: An Empirical Study Assessing Performance and Reuse Tasks

An analysis of incorporating an external language model into a sequence-to-sequence model

LSTM Neural Reordering Feature for Statistical Machine Translation

Deep API Learning

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision

Analogical Dissimilarity: Definition, Algorithms and Two Experiments in Machine Learning

Evaluating Pluralism in LLMs through Latent Perspectives

Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT Modules

AI Phenomenology for Understanding Human-AI Experiences Across Eras

Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice

Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting

Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection

Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation

Retrieving Versus Understanding Extractive Evidence in Few-Shot Learning

Identifying and interpreting non-aligned human conceptual representations using language modeling

Architecting Safer Autonomous Aviation Systems

Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder

Attacks and Faults Injection in Self-Driving Agents on the Carla Simulator -- Experience Report

A Study on Multimodal and Interactive Explanations for Visual Question Answering