大模型对齐与安全 - arXivDaily 专题

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

2304.13191 2023-04-27 cs.AI cs.CL 62%

Towards Explainable and Safe Conversational Agents for Mental Health: A Survey

Surjodeep Sarkar, Manas Gaur, L. Chen, Muskan Garg, Biplav Srivastava, Bhaktee Dongaonkar

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

Comments 10 pages, 3 figures, 2 tables

2303.01728 2023-04-25 cs.LG cs.AI cs.RO 62%

Guarded Policy Optimization with Imperfect Online Demonstrations

Zhenghai Xue, Zhenghao Peng, Quanyi Li, Zhihan Liu, Bolei Zhou

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

Comments Accepted at ICLR 2023 (top 25%)

2303.12558 2023-04-24 cs.LG cs.AI 62%

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

Florent Delgrange, Ann Nowé, Guillermo A. Pérez

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

Comments ICLR 2023, 10 pages main text, 14 pages appendix (excluding references)

2304.09448 2023-04-20 cs.LG cs.CL cs.CV 62%

EC^2: Emergent Communication for Embodied Control

Yao Mu, Shunyu Yao, Mingyu Ding, Ping Luo, Chuang Gan

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

Comments Published in CVPR2023

2304.06281 2023-04-14 cs.LG cs.AI cs.MA cs.RO 62%

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

Wenli Xiao, Yiwei Lyu, John Dolan

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

Comments Accepted in AAMAS 2023

2304.03081 2023-04-07 cs.LG cs.AI 62%

Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects

Siow Meng Low, Akshat Kumar, Scott Sanner

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

2209.15452 2023-03-21 cs.LG cs.AI cs.SY eess.SY stat.ML 62%

Safe Exploration Method for Reinforcement Learning under Existence of Disturbance

Yoshihiro Okawa, Tomotake Sasaki, Hitoshi Yanami, Toru Namerikawa

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

Comments Accepted by the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) 2022. The Version of Record is available at https://doi.org/10.1007/978-3-031-26412-2_9

2303.08187 2023-03-16 cs.LG cs.AI 62%

Vehicle lateral control using Machine Learning for automated vehicle guidance

Akash Fogla, Kanish Kumar, Sunnay Saurav, Bishnu ramanujan

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

2204.10416 2023-03-15 cs.LG cs.CY eess.SP 62%

CycleSense: Detecting Near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors

Ahmet-Serdar Karakaya, Thomas Ritter, Felix Biessmann, David Bermbach

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

2303.03226 2023-03-07 cs.AI cs.LG 62%

Safe Reinforcement Learning via Probabilistic Logic Shields

Wen-Chi Yang, Giuseppe Marra, Gavin Rens, Luc De Raedt

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

1. 安全训练 3309 篇

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

Towards Explainable and Safe Conversational Agents for Mental Health: A Survey

Guarded Policy Optimization with Imperfect Online Demonstrations

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

EC^2: Emergent Communication for Embodied Control

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects

Safe Exploration Method for Reinforcement Learning under Existence of Disturbance

Vehicle lateral control using Machine Learning for automated vehicle guidance

CycleSense: Detecting Near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors

Safe Reinforcement Learning via Probabilistic Logic Shields