arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

共收录 8057 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8057 篇

2412.13375 2025-01-09 cs.CL 57%

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation

Samin Mahdizadeh Sani, Pouya Sadeghi, Thuy-Trang Vu, Yadollah Yaghoobzadeh, Gholamreza Haffari

机构 * University of Tehran(德黑兰大学) Tehran Institute for Advanced Studies(德黑兰高等研究院) Khatam University(哈塔姆大学) Monash University(莫纳什大学)

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

Comments accepted at COLING 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.01958 2025-01-07 cs.CY 57%

A Survey on Food Ingredient Substitutions

Hyunwook Kim, Revathy Venkataramanan, Amit Sheth

专题命中 其他安全 :safety(abstract);分类 cs.CY

Comments 27 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.08936 2025-01-07 cs.MA cs.AI cs.RO 57%

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning

Peihong Yu, Manav Mishra, Alec Koppel, Carl Busart, Priya Narayan, Dinesh Manocha, Amrit Bedi, Pratap Tokekar

机构 * University of Maryland(马里兰大学) IISER Bhopal(博帕尔印度科学教育与研究所) JP Morgan Chase & Co.(摩根大通公司) DEVCOM Army Research Laboratory(DEVCOM陆军研究实验室) University of Central Florida(中佛罗里达大学)

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

Comments accepted in Transactions on Machine Learning Research

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.20715 2024-12-31 cs.MM cs.CL 57%

ChartAdapter: Large Vision-Language Model for Chart Summarization

Peixin Xu, Yujuan Ding, Wenqi Fan

机构 * The Hong Kong Polytechnic University(香港理工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.20682 2024-12-31 cs.CV cs.LG 57%

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks

Yuhe Ding, Bo Jiang, Aihua Zheng, Qin Xu, Jian Liang

机构 * School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院) School of Artificial Intelligence, Anhui University(安徽大学人工智能学院) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.16341 2024-12-31 cs.CL 57%

EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records

Yeonsu Kwon, Jiho Kim, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi

机构 * KAIST(韩国科学技术院) Samsung Medical Center(三星医疗中心) MIT(麻省理工学院) University of Toronto(多伦多大学)

专题命中 其他安全 :safety(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.00847 2024-12-31 cs.DB cs.AI cs.IR 57%

The Design of an LLM-powered Unstructured Analytics System

Eric Anderson, Jonathan Fritz, Austin Lee, Bohou Li, Mark Lindblad, Henry Lindeman, Alex Meyer, Parth Parmar, Tanvi Ranade, Mehul A. Shah, Benjamin Sowell, Dan Tecuci, Vinayak Thapliyal, Matt Welsh

机构 * Aryn, Inc(Aryn公司)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments Included in the proceedings of The Conference on Innovative Data Systems Research (CIDR) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.19609 2024-12-30 cs.GT cs.AI 57%

Bidding Games on Markov Decision Processes with Quantitative Reachability Objectives

Guy Avni, Martin Kurečka, Kaushik Mallik, Petr Novotný, Suman Sadhukhan

机构 * University of Haifa(海法大学) Masaryk University(马萨里克大学) Institute of Science and Technology Austria (ISTA)(奥地利科学技术研究所) IMDEA Software Institute(IMDEA软件研究所)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments To appear in AAMAS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.13069 2024-12-30 cs.CV cs.LG 57%

General-Purpose Multi-Modal OOD Detection Framework

Viet Duong, Qiong Wu, Zhengyi Zhou, Eric Zavesky, Jiahe Chen, Xiangzhou Liu, Wen-Ling Hsu, Huajie Shao

机构 * College of William and Mary(威廉玛丽学院) College of Control Science and Engineering(控制科学与工程学院) Zhejiang University(浙江大学) School of Computer Science(计算机学院) Department of Computer Science(计算机系)

专题命中 其他安全 :safety(abstract);分类 cs.LG

Journal ref Transactions on Machine Learning Research 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.18826 2024-12-30 cs.CL 57%

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Yilei Jiang, Yingshui Tan, Xiangyu Yue

机构 * The Chinese University of Hong Kong(香港中文大学) Alibaba Group(阿里巴巴集团)

专题命中 其他安全 :safety(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.18627 2024-12-30 cs.CL 57%

KRAIL: A Knowledge-Driven Framework for Base Human Reliability Analysis Integrating IDHEAS and Large Language Models

Xingyu Xiao, Peng Chen, Ben Qi, Hongru Zhao, Jingang Liang, Jiejuan Tong, Haitao Wang

机构 * Institute of Nuclear and New Energy Technology, Tsinghua University(清华大学核能与新能源技术研究院) Software Institute, Chinese Academy of Sciences(中国科学院软件研究所)

专题命中 其他安全 :safety(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.18273 2024-12-25 cs.CV cs.AI 57%

Sampling Bag of Views for Open-Vocabulary Object Detection

Hojun Choi, Junsuk Choe, Hyunjung Shim

机构 * KAIST AI(韩国科学技术院AI研究院) Sogang University(西江大学)

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

Comments 19 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.03094 2024-12-25 cs.AI 57%

A Divide-Align-Conquer Strategy for Program Synthesis

Jonas Witt, Sebastijan Dumančić, Tias Guns, Claus-Christian Carbon

机构 * University of Bamberg(班贝格大学) TU Delft(代尔夫特理工大学) KU Leuven(鲁汶大学)

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

Comments 11 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17794 2024-12-24 cs.LG 57%

Memory makes computation universal, remember?

Erik Garrison

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17171 2024-12-24 cs.LG cs.IR 57%

Enhancing Item Tokenization for Generative Recommendation through Self-Improvement

Runjin Chen, Mingxuan Ju, Ngoc Bui, Dimosthenis Antypas, Stanley Cai, Xiaopeng Wu, Leonardo Neves, Zhangyang Wang, Neil Shah, Tong Zhao

机构 * Snap Inc.(斯奈普公司) Yale University(耶鲁大学) Cardiff University(卡迪夫大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.16364 2024-12-24 cs.CV cs.CL 57%

A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation

Shijie Zhou, Ruiyi Zhang, Yufan Zhou, Changyou Chen

机构 * University at Buffalo(布法罗大学) Adobe Research(奥多比研究院)

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

Comments COLING 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00394 2024-12-24 cs.CY 57%

Analyzing Mass School Shootings in the United States from 1999 to 2024 with Game Theory, Probability Analysis, and Machine Learning

Wei Dai, Rui Zhang, Diya Kafle

专题命中 其他安全 :safety(abstract);分类 cs.CY

Comments 15 pages, 7 figures, conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.00333 2024-12-24 cs.CL 57%

Competence-Based Analysis of Language Models

Adam Davies, Jize Jiang, ChengXiang Zhai

机构 * Siebel School of Computing and Data Science(西贝尔计算与数据科学学院) The Grainger College of Engineering(格兰杰工程学院) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17886 2024-12-18 cs.CV cs.LG 57%

The Context of Crash Occurrence: A Complexity-Infused Approach Integrating Semantic, Contextual, and Kinematic Features

Meng Wang, Zach Noonan, Pnina Gershon, Bruce Mehler, Bryan Reimer, Shannon C. Roberts

机构 * University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) Massachusetts Institute of Technology(麻省理工学院)

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.00667 2024-12-18 cs.CL 57%

Does Vision Accelerate Hierarchical Generalization in Neural Language Learners?

Tatsuki Kuribayashi, Timothy Baldwin

机构 * MBZUAI(穆罕默德·本·扎耶德人工智能大学)

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

Comments COLING 2025; 15 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.12046 2024-12-17 cs.AI 57%

Artificial Intelligence in Traffic Systems

Ritwik Raj Saxena

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments 35 pages, 17343 words, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.10348 2024-12-16 cs.CV cs.AI 57%

A dual contrastive framework

Yuan Sun, Zhao Zhang, Jorge Ortiz

机构 * Rutgers University(罗格斯大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.09861 2024-12-16 cs.LG 57%

Data-Driven Transfer Learning Framework for Estimating Turning Movement Counts

Xiaobo Ma, Hyunsoo Noh, Ryan Hatch, James Tokishi, Zepu Wang

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.12435 2024-12-16 cs.CL 57%

Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models

Xinyu Zhou, Delong Chen, Samuel Cahyawijaya, Xufeng Duan, Zhenguang G. Cai

机构 * Université Paris Cité(巴黎西岱大学) Sorbonne Université(索邦大学) CUHK(香港中文大学) HKUST(香港科技大学) Cohere Brain and Mind Institute, CUHK(香港中文大学脑与心智研究所)

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

Comments COLING 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.07977 2024-12-16 cs.CL 57%

Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings

Saptarshi Sengupta, Connor Heaton, Suhan Cui, Soumalya Sarkar, Prasenjit Mitra

机构 * Pennsylvania State University(宾夕法尼亚州立大学) RTX Technology Research Center(RTX技术研究中心)

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

Comments Accepted to the MABM workshop at IEEE BIBM 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.10769 2024-12-16 cs.LG cs.CV 57%

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling

Shitong Shao, Xu Dai, Lujun Li, Huanran Chen, Yang Hu, Shouyi Yin

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Southeast University(东南大学) Hong Kong University of Science and Technology(香港科技大学) Tsinghua University(清华大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.09362 2024-12-13 cs.CL 57%

Falcon-UI: Understanding GUI Before Following User Instructions

Huawen Shen, Chang Liu, Gengluo Li, Xinlong Wang, Yu Zhou, Can Ma, Xiangyang Ji

机构 * Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) College of Computer Science, Nankai University(南开大学计算机学院) Department of Automation, Tsinghua University(清华大学自动化系) Beijing Academy of Artificial Intelligence(北京人工智能研究院) School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)

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

Comments 18 pages, 14 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.11147 2024-12-13 cs.CL 57%

Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning

Yukang Lin, Bingchen Zhong, Shuoran Jiang, Joanna Siebert, Qingcai Chen

机构 * Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Peng Cheng Laboratory(鹏城实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.08654 2024-12-13 cs.PL cs.AI cs.RO cs.SE 57%

A Behavior Tree-inspired programming language for autonomous agents

Oliver Biggar, Iman Shames

专题命中 其他安全 :safety(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.08161 2024-12-12 cs.CV cs.LG cs.MM cs.SD eess.AS 57%

Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation

Kexin Li, Zongxin Yang, Yi Yang, Jun Xiao

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

详情

展开后加载摘要…

URL PDF HTML 收藏