大模型对齐与安全

SoFA: Shielded On-the-fly Alignment via Priority Rule Following

Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li

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

Value alignment: a formal approach

Carles Sierra, Nardine Osman, Pablo Noriega, Jordi Sabater-Mir, Antoni Perelló

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

Comments accepted paper at the Responsible Artificial Intelligence Agents Workshop, of the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2019)

Journal ref Responsible Artificial Intelligence Agents Workshop (RAIA) at AAMAS 2019

Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment

Cong-Duy Nguyen, The-Anh Vu-Le, Thong Nguyen, Tho Quan, Luu Anh Tuan

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

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

Ziping Ma, Furong Xu, Jian Liu, Ming Yang, Qingpei Guo

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

Sample-Efficient Safety Assurances using Conformal Prediction

Rachel Luo, Shengjia Zhao, Jonathan Kuck, Boris Ivanovic, Silvio Savarese, Edward Schmerling, Marco Pavone

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

Comments International Journal of Robotics Research, 2023

Online Symbolic Music Alignment with Offline Reinforcement Learning

Silvan David Peter

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Journal ref Proceedings of the 24th International Society for Music Information Retrieval Conference, {ISMIR} 2023, Milan, Italy, November 5-9, 2023

GPT-4 and Safety Case Generation: An Exploratory Analysis

Mithila Sivakumar, Alvine Boaye Belle, Jinjun Shan, Kimya Khakzad Shahandashti

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

Quantum Kernel Alignment with Stochastic Gradient Descent

Gian Gentinetta, David Sutter, Christa Zoufal, Bryce Fuller, Stefan Woerner

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments 10 pages, 4 figures

Journal ref 2023 IEEE International Conference on Quantum Computing and Engineering (QCE)

LLMs for Multi-Modal Knowledge Extraction and Analysis in Intelligence/Safety-Critical Applications

Brett Israelsen, Soumalya Sarkar

专题命中 其他安全 ：safety(title,abstract)；分类 cs.CL

Comments initial draft

Can training neural language models on a curriculum with developmentally plausible data improve alignment with human reading behavior?

Aryaman Chobey, Oliver Smith, Anzi Wang, Grusha Prasad

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

Comments To appear in the proceedings of BabyLM shared task CoNLL 2023

Simulation-based Safety Assurance for an AVP System incorporating Learning-Enabled Components

Hasan Esen, Brian Hsuan-Cheng Liao

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

Comments 12 pages, 9 figures, 2 tables, presented at the 10th International Symposium on Development Methodology

healthAIChain: Improving security and safety using Blockchain Technology applications in AI-based healthcare systems

Naresh Kshetri, James Hutson, Revathy G

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

Comments 6 pages, 1 figure

Text Alignment Is An Efficient Unified Model for Massive NLP Tasks

Yuheng Zha, Yichi Yang, Ruichen Li, Zhiting Hu

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

Comments NeurIPS 2023 Camera Ready, Code available at https://github.com/yuh-zha/Align

Concept Alignment as a Prerequisite for Value Alignment

Sunayana Rane, Mark Ho, Ilia Sucholutsky, Thomas L. Griffiths

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

MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

Allen Nie, Yuhui Zhang, Atharva Amdekar, Chris Piech, Tatsunori Hashimoto, Tobias Gerstenberg

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

Comments 34 pages, 7 figures. NeurIPS 2023

Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning

Ananth Balashankar, Xiao Ma, Aradhana Sinha, Ahmad Beirami, Yao Qin, Jilin Chen, Alex Beutel

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

Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification

Rui Wang, Peipei Li, Huaibo Huang, Chunshui Cao, Ran He, Zhaofeng He

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

Comments Accepted by NeurIPS 2023

Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures

Thorsten Händler

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

Probabilistic Safety Regions Via Finite Families of Scalable Classifiers

Alberto Carlevaro, Teodoro Alamo, Fabrizio Dabbene, Maurizio Mongelli

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

Comments 13 pages, 4 figures, 1 table, submitted to IEEE TNNLS

ExpCLIP: Bridging Text and Facial Expressions via Semantic Alignment

Yicheng Zhong, Huawei Wei, Peiji Yang, Zhisheng Wang

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

LTLf Synthesis Under Environment Specifications for Reachability and Safety Properties

Benjamin Aminof, Giuseppe De Giacomo, Antonio Di Stasio, Hugo Francon, Sasha Rubin, Shufang Zhu

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

Comments To appear at EUMAS2023

Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound

W. A. P. Bastiaansen, M. Rousian, R. P. M. Steegers-Theunissen, W. J. Niessen, A. H. J. Koning, S. Klein

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://www.melba-journal.org/papers/2022:020.html

TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety

Ou Zheng, Mohamed Abdel-Aty, Dongdong Wang, Chenzhu Wang, Shengxuan Ding

专题命中 其他安全 ：safety(title,abstract)；分类 cs.CL

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment

Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, Tanmoy Chakraborty

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

Comments Accepted in ACL 2023. Code available at https://github.com/EshaanT/X-InSTA

Text-To-KG Alignment: Comparing Current Methods on Classification Tasks

Sondre Wold, Lilja Øvrelid, Erik Velldal

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

Comments Camera ready version for MATCHING workshop at ACL 2023

Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation

Le Zhang, Jiayang Chen, Tao Shen, Yu Li, Siqi Sun

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Analyzing Text Representations by Measuring Task Alignment

Cesar Gonzalez-Gutierrez, Audi Primadhanty, Francesco Cazzaro, Ariadna Quattoni

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

Comments arXiv admin note: text overlap with arXiv:2210.05721

From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment

Yu Zhao, Yike Wu, Xiangrui Cai, Ying Zhang, Haiwei Zhang, Xiaojie Yuan

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

Comments Accepted by ACL 2023 Findings

Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach

Maha Riad, Vinicius Renan de Carvalho, Fatemeh Golpayegani

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

RAFEN -- Regularized Alignment Framework for Embeddings of Nodes

Kamil Tagowski, Piotr Bielak, Jakub Binkowski, Tomasz Kajdanowicz

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments ICCS 2023