大模型对齐与安全

Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes

Krishna C. Kalagarla, Dhruva Kartik, Dongming Shen, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2203.09038

What If We Recaption Billions of Web Images with LLaMA-3?

Xianhang Li, Haoqin Tu, Mude Hui, Zeyu Wang, Bingchen Zhao, Junfei Xiao, Sucheng Ren, Jieru Mei, Qing Liu, Huangjie Zheng, Yuyin Zhou, Cihang Xie

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

Comments First five authors contributed equally

Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners

Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

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

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham

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

Comments In Forty-first International Conference on Machine Learning, 2024. Code at https://github.com/MedARC-AI/MindEyeV2. Published as a conference paper at ICML 2024

GEB-1.3B: Open Lightweight Large Language Model

Jie Wu, Yufeng Zhu, Lei Shen, Xuqing Lu

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

Comments GEB-1.3B technical report

SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data

Abdulrahman Alabdulkareem, Christian M Arnold, Yerim Lee, Pieter M Feenstra, Boris Katz, Andrei Barbu

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Decipherment-Aware Multilingual Learning in Jointly Trained Language Models

Grandee Lee

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

Coherent Zero-Shot Visual Instruction Generation

Quynh Phung, Songwei Ge, Jia-Bin Huang

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

Comments https://instruct-vis-zero.github.io/

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Pengyuan Zhou

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments Accepted to ACL'24 (Findings)

BLSP-Emo: Towards Empathetic Large Speech-Language Models

Chen Wang, Minpeng Liao, Zhongqiang Huang, Junhong Wu, Chengqing Zong, Jiajun Zhang

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

Reasons to Reject? Aligning Language Models with Judgments

Weiwen Xu, Deng Cai, Zhisong Zhang, Wai Lam, Shuming Shi

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

Comments Accepted at ACL 2024 Findings. Our source codes and models are publicly available at https://github.com/wwxu21/CUT

Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation

Tingjia Shen, Hao Wang, Jiaqing Zhang, Sirui Zhao, Liangyue Li, Zulong Chen, Defu Lian, Enhong Chen

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

Comments 10 pages, 5 figures

Unified Explanations in Machine Learning Models: A Perturbation Approach

Jacob Dineen, Don Kridel, Daniel Dolk, David Castillo

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

Unveiling Linguistic Regions in Large Language Models

Zhihao Zhang, Jun Zhao, Qi Zhang, Tao Gui, Xuanjing Huang

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

Comments Accepted by ACL 2024. Camera-Ready Version

Deciphering Human Mobility: Inferring Semantics of Trajectories with Large Language Models

Yuxiao Luo, Zhongcai Cao, Xin Jin, Kang Liu, Ling Yin

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Position: Foundation Agents as the Paradigm Shift for Decision Making

Xiaoqian Liu, Xingzhou Lou, Jianbin Jiao, Junge Zhang

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

Comments 17 pages, camera-ready version of ICML 2024

Blind Data Adaptation to tackle Covariate Shift in Operational Steganalysis

Rony Abecidan, Vincent Itier, Jérémie Boulanger, Patrick Bas, Tomáš Pevný

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

WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization

Jiawei Ma, Yulei Niu, Shiyuan Huang, Guangxing Han, Shih-Fu Chang

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

Interpretable Prognostics with Concept Bottleneck Models

Florent Forest, Katharina Rombach, Olga Fink

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Under review

Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity

Shanghaoran Quan

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

Maintaining and Managing Road Quality:Using MLP and DNN

Makgotso Jacqueline Maotwana

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention

Andrew Li, Xianle Feng, Siddhant Narang, Austin Peng, Tianle Cai, Raj Sanjay Shah, Sashank Varma

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

Comments Accepted by CogSci-24

Towards a Framework for Openness in Foundation Models: Proceedings from the Columbia Convening on Openness in Artificial Intelligence

Adrien Basdevant, Camille François, Victor Storchan, Kevin Bankston, Ayah Bdeir, Brian Behlendorf, Merouane Debbah, Sayash Kapoor, Yann LeCun, Mark Surman, Helen King-Turvey, Nathan Lambert, Stefano Maffulli, Nik Marda, Govind Shivkumar, Justine Tunney

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Hybrid Context Retrieval Augmented Generation Pipeline: LLM-Augmented Knowledge Graphs and Vector Database for Accreditation Reporting Assistance

Candace Edwards

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

Comments 17 pages, 9 figures

MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation

Shuwen Qiu, Mingdian Liu, Hengli Li, Song-Chun Zhu, Zilong Zheng

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

Towards Contactless Elevators with TinyML using CNN-based Person Detection and Keyword Spotting

Anway S. Pimpalkar, Deeplaxmi V. Niture

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

EduceLab-Scrolls: Verifiable Recovery of Text from Herculaneum Papyri using X-ray CT

Stephen Parsons, C. Seth Parker, Christy Chapman, Mami Hayashida, W. Brent Seales

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

Unveiling Key Aspects of Fine-Tuning in Sentence Embeddings: A Representation Rank Analysis

Euna Jung, Jaeill Kim, Jungmin Ko, Jinwoo Park, Wonjong Rhee

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

Knowledge-augmented Graph Neural Networks with Concept-aware Attention for Adverse Drug Event Detection

Shaoxiong Ji, Ya Gao, Pekka Marttinen

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments LREC-COLING 2024

Testing learning-enabled cyber-physical systems with Large-Language Models: A Formal Approach

Xi Zheng, Aloysius K. Mok, Ruzica Piskac, Yong Jae Lee, Bhaskar Krishnamachari, Dakai Zhu, Oleg Sokolsky, Insup Lee

专题命中 其他安全 ：safety(abstract)；分类 cs.AI