大模型对齐与安全 - arXivDaily 专题

2410.03223 2024-10-07 cs.CL 57%

Consultation on Industrial Machine Faults with Large language Models

Apiradee Boonmee, Kritsada Wongsuwan, Pimchanok Sukjai

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments 9 pages

2404.11972 2024-10-07 cs.CL 57%

Aligning Language Models to Explicitly Handle Ambiguity

Hyuhng Joon Kim, Youna Kim, Cheonbok Park, Junyeob Kim, Choonghyun Park, Kang Min Yoo, Sang-goo Lee, Taeuk Kim

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments EMNLP 2024 (main)

2410.02271 2024-10-04 cs.SD cs.AI eess.AS 57%

CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation

Junda Wu, Warren Li, Zachary Novack, Amit Namburi, Carol Chen, Julian McAuley

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments 4 pages

2406.12354 2024-10-04 cs.CL 57%

Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models

Minseok Choi, Kyunghyun Min, Jaegul Choo

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments EMNLP 2024 Findings

2404.15206 2024-10-04 cs.CL 57%

Does Instruction Tuning Make LLMs More Consistent?

Constanza Fierro, Jiaang Li, Anders Søgaard

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments We need to run extra experiments to ensure some of the claims in the paper are fully correct

2212.00596 2024-10-04 cs.CL q-bio.NC 57%

Language models and brains align due to more than next-word prediction and word-level information

Gabriele Merlin, Mariya Toneva

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2024

2409.16911 2024-10-03 cs.CL 57%

Pruning Multilingual Large Language Models for Multilingual Inference

Hwichan Kim, Jun Suzuki, Tosho Hirasawa, Mamoru Komachi

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2024 Findings

2409.20424 2024-10-01 cs.CV cs.AI 57%

World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

Jiacong Wang, Bohong Wu, Haiyong Jiang, Xun Zhou, Xin Xiao, Haoyuan Guo, Jun Xiao

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments Accepted at EMNLP 2024 Main Conference, 16pages

2409.19961 2024-10-01 cs.CV cs.CL 57%

Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval

Yabing Wang, Le Wang, Qiang Zhou, Zhibin Wang, Hao Li, Gang Hua, Wei Tang

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted by ACM Multimedia

2409.19696 2024-10-01 cs.LG cs.CV 57%

Vision-Language Models are Strong Noisy Label Detectors

Tong Wei, Hao-Tian Li, Chun-Shu Li, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Accepted at NeurIPS 2024

2409.19650 2024-10-01 cs.CV cs.AI 57%

Grounding 3D Scene Affordance From Egocentric Interactions

Cuiyu Liu, Wei Zhai, Yuhang Yang, Hongchen Luo, Sen Liang, Yang Cao, Zheng-Jun Zha

专题命中其他安全：alignment(abstract)；分类 cs.AI

2409.19270 2024-10-01 cs.SD cs.AI eess.AS 57%

OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation

Tanvir Mahmud, Diana Marculescu

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments Accepted in EMNLP 2024 Main

2405.05417 2024-09-30 cs.CL 57%

Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models

Sander Land, Max Bartolo

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments 16 pages, 6 figures. Accepted at EMNLP 2024, main track. For associated code, see https://github.com/cohere-ai/magikarp/

2409.16830 2024-09-26 cs.RO cs.AI 57%

OffRIPP: Offline RL-based Informative Path Planning

Srikar Babu Gadipudi, Srujan Deolasee, Siva Kailas, Wenhao Luo, Katia Sycara, Woojun Kim

专题命中其他安全：safety(abstract)；分类 cs.AI

Comments 7 pages, 6 figures, submitted to ICRA 2025

2409.15322 2024-09-25 physics.chem-ph cs.LG 57%

AI and Machine Learning Approaches for Predicting Nanoparticles Toxicity The Critical Role of Physiochemical Properties

Iqra Yousaf

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments 20 pages, 14 figures. Presented at the International Conference on Nanotechnology and Smart Materials 2024. Includes supplementary material

2409.15310 2024-09-25 cs.LG cs.CV 57%

Visual Prompting in Multimodal Large Language Models: A Survey

Junda Wu, Zhehao Zhang, Yu Xia, Xintong Li, Zhaoyang Xia, Aaron Chang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ruiyi Zhang, Subrata Mitra, Dimitris N. Metaxas, Lina Yao, Jingbo Shang, Julian McAuley

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments 10 pages

2409.14473 2024-09-24 cs.CE cs.CL 57%

A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language

Nikita Kartashov, Nikolaos N. Vlassis

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments 29 pages, 15 figures

2409.13926 2024-09-24 cs.AI cs.HC 57%

SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

Nels Numan, Shwetha Rajaram, Balasaravanan Thoravi Kumaravel, Nicolai Marquardt, Andrew D. Wilson

专题命中其他安全：alignment(abstract)；分类 cs.AI

2406.08959 2024-09-23 cs.HC cs.AI 57%

Beyond Recommendations: From Backward to Forward AI Support of Pilots' Decision-Making Process

Zelun Tony Zhang, Sebastian S. Feger, Lucas Dullenkopf, Rulu Liao, Lukas Süsslin, Yuanting Liu, Andreas Butz

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments Accepted to CSCW 2024, to be published in PACM HCI Vol. 8, No. CSCW2

2409.12801 2024-09-20 cs.HC cs.AI 57%

Exploring the Lands Between: A Method for Finding Differences between AI-Decisions and Human Ratings through Generated Samples

Lukas Mecke, Daniel Buschek, Uwe Gruenefeld, Florian Alt

专题命中其他安全：alignment(abstract)；分类 cs.AI

2401.00713 2024-09-20 cs.LG 57%

Graph Neural Networks in Intelligent Transportation Systems: Advances, Applications and Trends

Hourun Li, Yusheng Zhao, Zhengyang Mao, Yifang Qin, Zhiping Xiao, Jiaqi Feng, Yiyang Gu, Wei Ju, Xiao Luo, Ming Zhang

专题命中其他安全：safety(abstract)；分类 cs.LG

2409.10921 2024-09-18 cs.CV cs.AI 57%

KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph

Yanbei Jiang, Krista A. Ehinger, Jey Han Lau

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments Accepted at IJCAI 2024

2403.12958 2024-09-18 cs.CL 57%

Dated Data: Tracing Knowledge Cutoffs in Large Language Models

Jeffrey Cheng, Marc Marone, Orion Weller, Dawn Lawrie, Daniel Khashabi, Benjamin Van Durme

专题命中其他安全：alignment(abstract)；分类 cs.CL

2409.08147 2024-09-13 cs.CL 57%

LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Models

Zhengliang Liu, Yiwei Li, Oleksandra Zolotarevych, Rongwei Yang, Tianming Liu

专题命中其他安全：alignment(abstract)；分类 cs.CL

2409.07918 2024-09-13 cs.HC cs.AI cs.SD eess.AS 57%

Tidal MerzA: Combining affective modelling and autonomous code generation through Reinforcement Learning

Elizabeth Wilson, György Fazekas, Geraint Wiggins

专题命中其他安全：alignment(abstract)；分类 cs.AI

2303.13173 2024-09-12 cs.SE cs.AI 57%

Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository

Lukas Heiland, Marius Hauser, Justus Bogner

专题命中其他安全：safety(abstract)；分类 cs.AI

Comments Accepted for publication at the International Conference on AI Engineering (CAIN) 2023

2403.00884 2024-09-09 cs.DB cs.AI cs.IR 57%

Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment

Margherita Martorana, Tobias Kuhn, Lise Stork, Jacco van Ossenbruggen

专题命中其他安全：alignment(abstract)；分类 cs.AI

2409.03440 2024-09-06 cs.CL 57%

Rx Strategist: Prescription Verification using LLM Agents System

Phuc Phan Van, Dat Nguyen Minh, An Dinh Ngoc, Huy Phan Thanh

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments 17 Pages, 6 Figures, Under Review

2409.01232 2024-09-04 cs.CL 57%

THInC: A Theory-Driven Framework for Computational Humor Detection

Victor De Marez, Thomas Winters, Ayla Rigouts Terryn

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted at CREAI 2024 (International Workshop on Artificial Intelligence and Creativity)

2409.00880 2024-09-04 cs.LG 57%

Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment

Aditya Bansal, Michael Yuhas, Arvind Easwaran

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments Accepted to IEEE RTCSA 2024

1. 其他安全 8057 篇

Consultation on Industrial Machine Faults with Large language Models

Aligning Language Models to Explicitly Handle Ambiguity

CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation

Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models

Does Instruction Tuning Make LLMs More Consistent?

Language models and brains align due to more than next-word prediction and word-level information

Pruning Multilingual Large Language Models for Multilingual Inference

World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval

Vision-Language Models are Strong Noisy Label Detectors

Grounding 3D Scene Affordance From Egocentric Interactions

OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation

Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models

OffRIPP: Offline RL-based Informative Path Planning

AI and Machine Learning Approaches for Predicting Nanoparticles Toxicity The Critical Role of Physiochemical Properties

Visual Prompting in Multimodal Large Language Models: A Survey

A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language

SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

Beyond Recommendations: From Backward to Forward AI Support of Pilots' Decision-Making Process

Exploring the Lands Between: A Method for Finding Differences between AI-Decisions and Human Ratings through Generated Samples

Graph Neural Networks in Intelligent Transportation Systems: Advances, Applications and Trends

KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph

Dated Data: Tracing Knowledge Cutoffs in Large Language Models

LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Models

Tidal MerzA: Combining affective modelling and autonomous code generation through Reinforcement Learning

Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository

Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment

Rx Strategist: Prescription Verification using LLM Agents System

THInC: A Theory-Driven Framework for Computational Humor Detection

Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment