大模型对齐与安全 - arXivDaily 专题

2401.13275 2024-01-30 cs.CL cs.AI 62%

Can AI Assistants Know What They Don't Know?

Qinyuan Cheng, Tianxiang Sun, Xiangyang Liu, Wenwei Zhang, Zhangyue Yin, Shimin Li, Linyang Li, Zhengfu He, Kai Chen, Xipeng Qiu

专题命中安全训练：alignment(abstract)；分类 cs.CL、cs.AI

Comments Work in progress

2110.11334 2024-01-24 cs.CV cs.AI cs.LG 62%

Generalized Out-of-Distribution Detection: A Survey

Jingkang Yang, Kaiyang Zhou, Yixuan Li, Ziwei Liu

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments Feel free to comment on our Overleaf manuscript: https://www.overleaf.com/9899719915wmccvdtwpkct#c25192

2309.13365 2024-01-23 cs.LG cs.AI 62%

Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs

Hector Kohler, Riad Akrour, Philippe Preux

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments To be included in an other submission. arXiv admin note: text overlap with arXiv:2304.05839

2308.07272 2024-01-17 cs.LG cs.CL 62%

Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning

Chengzhengxu Li, Xiaoming Liu, Yichen Wang, Duyi Li, Yu Lan, Chao Shen

专题命中安全训练：alignment(abstract)；分类 cs.CL、cs.LG

Comments AAAI 2024 Main Track

2401.03786 2024-01-12 cs.LG cs.AI cs.RO 62%

Long-term Safe Reinforcement Learning with Binary Feedback

Akifumi Wachi, Wataru Hashimoto, Kazumune Hashimoto

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted to AAAI-24

2308.11339 2024-01-12 cs.AI cs.LG cs.MA 62%

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang

专题命中安全训练：alignment(abstract)；分类 cs.AI、cs.LG

Comments v3 is the AAAI'24 camera ready version, which polished abstract and introduction based on the reviewers' comments, and enriched related works. 7 pages of main content, 2 pages of references, 2 figures and 1 table

2302.10639 2024-01-10 cs.AI cs.LG 62%

Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning

Yuxiao Lu, Arunesh Sinha, Pradeep Varakantham

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 10 figures

2303.01141 2023-12-15 cs.LG cs.AI 62%

DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction

Kshitij Goyal, Sebastijan Dumancic, Hendrik Blockeel

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments 13 pages

2312.06436 2023-12-13 cs.LG cs.AI 62%

Reward Certification for Policy Smoothed Reinforcement Learning

Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang, Yanghao Zhang, Xiaowei Huang, Wenjie Ruan

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments This paper will be presented in AAAI2024

2311.02227 2023-12-13 cs.LG cs.AI cs.SY eess.SY 62%

State-Wise Safe Reinforcement Learning With Pixel Observations

Simon Sinong Zhan, Yixuan Wang, Qingyuan Wu, Ruochen Jiao, Chao Huang, Qi Zhu

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 5 figures

2210.01241 2023-12-05 cs.CL cs.LG 62%

Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Rajkumar Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, Yejin Choi

专题命中安全训练：alignment(abstract)；分类 cs.CL、cs.LG

Comments In Proceedings of ICLR 2023. Code found at https://github.com/allenai/rl4lms and Project website at https://rl4lms.apps.allenai.org/

2310.17769 2023-12-05 cs.CL cs.AI 62%

Social Contract AI: Aligning AI Assistants with Implicit Group Norms

Jan-Philipp Fränken, Sam Kwok, Peixuan Ye, Kanishk Gandhi, Dilip Arumugam, Jared Moore, Alex Tamkin, Tobias Gerstenberg, Noah D. Goodman

专题命中安全训练：alignment(abstract)；分类 cs.CL、cs.AI

Comments SoLaR NeurIPS 2023 Workshop (https://solar-neurips.github.io/)

2311.08592 2023-12-01 cs.SE cs.AI cs.CL 62%

AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications

Bhaktipriya Radharapu, Kevin Robinson, Lora Aroyo, Preethi Lahoti

专题命中安全训练：safety(abstract)；分类 cs.CL、cs.AI

2311.10863 2023-11-23 cs.RO cs.AI cs.LG 62%

Verified Compositional Neuro-Symbolic Control for Stochastic Systems with Temporal Logic Tasks

Jun Wang, Haojun Chen, Zihe Sun, Yiannis Kantaros

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: substantial text overlap with arXiv:2209.06130

2311.03033 2023-11-07 cs.LG cs.AI 62%

Beyond Words: A Mathematical Framework for Interpreting Large Language Models

Javier González, Aditya V. Nori

专题命中安全训练：alignment(abstract)；分类 cs.AI、cs.LG

Comments 4 figures, 18 pages

2311.00063 2023-11-02 cs.RO cs.AI cs.LG cs.MA cs.SY eess.SY 62%

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning

Sleiman Safaoui, Abraham P. Vinod, Ankush Chakrabarty, Rien Quirynen, Nobuyuki Yoshikawa, Stefano Di Cairano

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

2310.20287 2023-11-01 cs.LG cs.AI 62%

Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents

Woojun Kim, Yongjae Shin, Jongeui Park, Youngchul Sung

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2023 camera-ready

2310.14788 2023-10-24 cs.LG cs.AI cs.SY eess.SY 62%

Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces

Ammar N. Abbas, Georgios C. Chasparis, John D. Kelleher

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

2310.10501 2023-10-17 cs.CL cs.AI 62%

NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails

Traian Rebedea, Razvan Dinu, Makesh Sreedhar, Christopher Parisien, Jonathan Cohen

专题命中安全训练：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2023 - Demo track

2310.08595 2023-10-17 cs.RO cs.AI cs.LG 62%

Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation

Badr Ben Elallid, Hamza El Alaoui, Nabil Benamar

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted for publication in the 2023 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

2309.10007 2023-10-03 cs.RO cs.AI cs.LG cs.MA 62%

Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem

Tanmay Vilas Samak, Chinmay Vilas Samak, Venkat Krovi

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted as Multi-Agent Dynamic Games (MAD-Games) Workshop Paper at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023

2309.04707 2023-09-12 cs.AI cs.LG 62%

Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective

Muzhe Guo, Feixu Yu, Tian Lan, Fang Jin

专题命中安全训练：trustworthy(abstract)；分类 cs.AI、cs.LG

2308.12270 2023-08-24 cs.LG cs.AI 62%

Language Reward Modulation for Pretraining Reinforcement Learning

Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Younggyo Seo, Stephen James, Pieter Abbeel

专题命中安全训练：alignment(abstract)；分类 cs.AI、cs.LG

Comments Code available at https://github.com/ademiadeniji/lamp

2303.10130 2023-08-22 econ.GN cs.AI cs.CY q-fin.EC 62%

GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

Tyna Eloundou, Sam Manning, Pamela Mishkin, Daniel Rock

专题命中安全训练：alignment(abstract)；分类 cs.AI、cs.CY

2308.03907 2023-08-09 cs.HC cs.CY cs.LG 62%

Advancements In Crowd-Monitoring System: A Comprehensive Analysis of Systematic Approaches and Automation Algorithms: State-of-The-Art

Mohammed Ameen, Richard Stone

专题命中安全训练：safety(abstract)；分类 cs.CY、cs.LG

2206.07813 2023-08-08 cs.SE cs.AI cs.LG 62%

A Search-Based Testing Approach for Deep Reinforcement Learning Agents

Amirhossein Zolfagharian, Manel Abdellatif, Lionel Briand, Mojtaba Bagherzadeh, Ramesh S

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Journal ref in IEEE Transactions on Software Engineering, vol. 49, no. 7, pp. 3715-3735, July 2023

2306.13944 2023-06-27 cs.LG cs.AI 62%

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

Xiao Zhang, Hai Zhang, Hongtu Zhou, Chang Huang, Di Zhang, Chen Ye, Junqiao Zhao

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 5 figures

2206.02670 2023-06-21 cs.LG cs.AI cs.CR cs.RO 62%

Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning

Thomas Hickling, Nabil Aouf, Phillippa Spencer

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

Comments 13 pages, 16 figures

2306.09055 2023-06-16 cs.RO cs.AI cs.LG 62%

Predictive Maneuver Planning with Deep Reinforcement Learning (PMP-DRL) for comfortable and safe autonomous driving

Jayabrata Chowdhury, Vishruth Veerendranath, Suresh Sundaram, Narasimhan Sundararajan

专题命中安全训练：safety(abstract)；分类 cs.AI、cs.LG

2302.02337 2023-05-15 cs.CY cs.AI 62%

Regulating ChatGPT and other Large Generative AI Models

Philipp Hacker, Andreas Engel, Marco Mauer

专题命中安全训练：trustworthy(abstract)；分类 cs.AI、cs.CY

Comments FAccT '23, June 12-15, 2023, Chicago, IL, USA

1. 安全训练 3278 篇

Can AI Assistants Know What They Don't Know?

Generalized Out-of-Distribution Detection: A Survey

Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs

Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning

Long-term Safe Reinforcement Learning with Binary Feedback

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning

DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction

Reward Certification for Policy Smoothed Reinforcement Learning

State-Wise Safe Reinforcement Learning With Pixel Observations

Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Social Contract AI: Aligning AI Assistants with Implicit Group Norms

AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications

Verified Compositional Neuro-Symbolic Control for Stochastic Systems with Temporal Logic Tasks

Beyond Words: A Mathematical Framework for Interpreting Large Language Models

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning

Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents

Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces

NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails

Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation

Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem

Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective

Language Reward Modulation for Pretraining Reinforcement Learning

GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

Advancements In Crowd-Monitoring System: A Comprehensive Analysis of Systematic Approaches and Automation Algorithms: State-of-The-Art

A Search-Based Testing Approach for Deep Reinforcement Learning Agents

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning

Predictive Maneuver Planning with Deep Reinforcement Learning (PMP-DRL) for comfortable and safe autonomous driving

Regulating ChatGPT and other Large Generative AI Models