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。

2025-08-07 至 2025-08-07 共收录 10 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 10 篇

2508.02762 2025-08-07 cs.LG cs.AI 81%

Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment

Dahun Kim, Anelia Angelova

机构 * Google DeepMind(谷歌DeepMind)

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

Comments COLM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09485 2025-08-07 cs.LG cs.AR 79%

GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder Alignment

Wenji Fang, Jing Wang, Yao Lu, Shang Liu, Zhiyao Xie

机构 * Hong Kong University of Science and Technology(香港理工大学)

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

Comments Accepted by ICCAD'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01602 2025-08-07 cs.CV 78%

Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment

Lubin Gan, Jing Zhang, Linhao Qu, Yijun Wang, Siying Wu, Xiaoyan Sun

机构 * University of Science and Technology of China(科学技术大学) Fudan University(复旦大学)

专题命中 其他安全 :alignment(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04571 2025-08-07 cs.IR cs.CL cs.LG 62%

Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation

Claudio Pomo, Matteo Attimonelli, Danilo Danese, Fedelucio Narducci, Tommaso Di Noia

机构 * Sapienza University of Rome(罗马大学)

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

Comments Accepted as Full Research Papers at CIKM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04073 2025-08-07 cs.CL cs.LG 62%

Efficient Strategy for Improving Large Language Model (LLM) Capabilities

Julián Camilo Velandia Gutiérrez

机构 * Universidad Nacional de Colombia(哥伦比亚国立大学)

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

Comments Based on master's thesis in Systems and Computer Engineering, Universidad Nacional de Colombia (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.17963 2025-08-07 cs.LG cs.AI 62%

Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks

Xingcheng Xu, Zibo Zhao, Haipeng Zhang, Yanqing Yang

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ShanghaiTech University(上海科技大学) University of Hong Kong(香港大学) Fudan University(复旦大学)

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

Comments Accepted by the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Main Conference

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.14805 2025-08-07 cs.CL 57%

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Julia Kharchenko, Tanya Roosta, Aman Chadha, Chirag Shah

机构 * University of Washington(华盛顿大学) UC Berkeley, Amazon(伯克利大学、亚马逊) Stanford University, Amazon GenAI(斯坦福大学、亚马逊生成人工智能)

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

Comments KDD 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04572 2025-08-07 cs.CV 50%

Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding

Jun Li, Che Liu, Wenjia Bai, Mingxuan Liu, Rossella Arcucci, Cosmin I. Bercea, Julia A. Schnabel

机构 * Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) Imperial College London(伦敦帝国学院) University of Trento(特伦托大学) Helmholtz AI and Helmholtz Munich(海德堡人工智能与海德堡慕尼黑) King’s College London(伦敦国王学院)

专题命中 其他安全 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17342 2025-08-07 cs.CV 50%

DeMo++: Motion Decoupling for Autonomous Driving

Bozhou Zhang, Nan Song, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University(复旦大学数据科学学院) University of Surrey(萨里大学)

专题命中 其他安全 :safety(abstract)

Comments Journal extension of NeurIPS 2024. arXiv admin note: substantial text overlap with arXiv:2410.05982

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10416 2025-08-07 cs.MM cs.SD eess.AS 50%

Can Sound Replace Vision in LLaVA With Token Substitution?

Ali Vosoughi, Jing Bi, Pinxin Liu, Yunlong Tang, Chenliang Xu

专题命中 其他安全 :alignment(abstract)

Comments Project page: https://ali-vosoughi.github.io/SoundCLIP/

详情

展开后加载摘要…

URL PDF HTML 收藏