大模型对齐与安全 - arXivDaily 专题

2406.06397 2024-10-11 q-bio.BM cs.AI cs.LG 62%

Contrastive learning of T cell receptor representations

Yuta Nagano, Andrew Pyo, Martina Milighetti, James Henderson, John Shawe-Taylor, Benny Chain, Andreas Tiffeau-Mayer

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

Comments 25 pages, 23 figures; additional analyses and improvements to existing figures

2410.06225 2024-10-10 cs.LG cs.AI 62%

A Timeline and Analysis for Representation Plasticity in Large Language Models

Akshat Kannan

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

2410.03696 2024-10-08 cs.HC cs.AI cs.LG eess.SP 62%

Improving Emotion Recognition Accuracy with Personalized Clustering

Laura Gutierrez-Martin, Celia Lopez Ongil, Jose M. Lanza-Gutierrez, Jose A. Miranda Calero

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

Comments 11 pages, 2 figures

2410.03770 2024-10-08 cs.CL cs.AI 62%

A Two-Stage Proactive Dialogue Generator for Efficient Clinical Information Collection Using Large Language Model

Xueshen Li, Xinlong Hou, Nirupama Ravi, Ziyi Huang, Yu Gan

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

Comments Prepare for submission

2410.03752 2024-10-08 cs.SD cs.AI cs.CL eess.AS 62%

Efficient Streaming LLM for Speech Recognition

Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli

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

2410.03134 2024-10-07 cs.LG cs.AI eess.SP 62%

Remaining Useful Life Prediction: A Study on Multidimensional Industrial Signal Processing and Efficient Transfer Learning Based on Large Language Models

Yan Chen, Cheng Liu

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

2408.16221 2024-10-07 eess.AS cs.AI cs.CL cs.SD 62%

SSDM: Scalable Speech Dysfluency Modeling

Jiachen Lian, Xuanru Zhou, Zoe Ezzes, Jet Vonk, Brittany Morin, David Baquirin, Zachary Mille, Maria Luisa Gorno Tempini, Gopala Krishna Anumanchipalli

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

Comments 2024 NeurIPS

2410.02740 2024-10-04 cs.CV cs.AI cs.LG 62%

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Zhengfeng Lai, Vasileios Saveris, Chen Chen, Hong-You Chen, Haotian Zhang, Bowen Zhang, Juan Lao Tebar, Wenze Hu, Zhe Gan, Peter Grasch, Meng Cao, Yinfei Yang

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

Comments CV/ML

2405.14394 2024-10-04 cs.CL cs.AI 62%

Instruction Tuning With Loss Over Instructions

Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani

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

Comments NeurIPS 2024. Code is available at https://github.com/ZhengxiangShi/InstructionModelling

2410.01450 2024-10-03 cs.CL cs.AI 62%

Agent-Driven Large Language Models for Mandarin Lyric Generation

Hong-Hsiang Liu, Yi-Wen Liu

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

Comments 6 pages, figures, Accepted at O-COCOSDA 2024

2409.12963 2024-10-03 cs.CV cs.AI cs.LG 62%

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Yuzhang Shang, Bingxin Xu, Weitai Kang, Mu Cai, Yuheng Li, Zehao Wen, Zhen Dong, Kurt Keutzer, Yong Jae Lee, Yan Yan

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

2402.15062 2024-10-03 cs.CL cs.LG 62%

Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations

Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua

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

2410.00513 2024-10-02 cs.CL cs.AI 62%

Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

Deokhyung Kang, Seonjeong Hwang, Yunsu Kim, Gary Geunbae Lee

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

Comments Accepted to EMNLP 2024

2409.03256 2024-10-01 cs.CL cs.AI 62%

E2CL: Exploration-based Error Correction Learning for Embodied Agents

Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li

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

Comments Accepted by EMNLP 2024

2409.18286 2024-09-30 cs.CV cs.AI cs.CL 62%

Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing

Huthaifa I. Ashqar, Ahmed Jaber, Taqwa I. Alhadidi, Mohammed Elhenawy

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

2409.17683 2024-09-27 cs.CL cs.AI 62%

Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT

Natthanaphop Isaradech, Andrea Riedel, Wachiranun Sirikul, Markus Kreuzthaler, Stefan Schulz

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

2409.13731 2024-09-27 cs.CL cs.AI 62%

KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation

Lei Liang, Mengshu Sun, Zhengke Gui, Zhongshu Zhu, Zhouyu Jiang, Ling Zhong, Yuan Qu, Peilong Zhao, Zhongpu Bo, Jin Yang, Huaidong Xiong, Lin Yuan, Jun Xu, Zaoyang Wang, Zhiqiang Zhang, Wen Zhang, Huajun Chen, Wenguang Chen, Jun Zhou

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

Comments 33 pages

2409.17416 2024-09-27 cs.CL cs.AI 62%

From Deception to Detection: The Dual Roles of Large Language Models in Fake News

Dorsaf Sallami, Yuan-Chen Chang, Esma Aïmeur

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

2409.15338 2024-09-25 cs.CY cs.AI 62%

Explainable AI: Definition and attributes of a good explanation for health AI

Evangelia Kyrimi, Scott McLachlan, Jared M Wohlgemut, Zane B Perkins, David A. Lagnado, William Marsh, the ExAIDSS Expert Group

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.CY

Comments 21 pages

2409.14436 2024-09-24 cs.CL cs.AI cs.RO 62%

Automotive innovation landscaping using LLM

Raju Gorain, Omkar Salunke

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

Comments 9pages, 4Figures, 1 Flow chart

2409.14381 2024-09-24 cs.CL cs.LG 62%

Investigating Layer Importance in Large Language Models

Yang Zhang, Yanfei Dong, Kenji Kawaguchi

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

2403.20058 2024-09-23 eess.IV cs.AI cs.CV cs.LG 62%

Revolutionizing Disease Diagnosis with simultaneous functional PET/MR and Deeply Integrated Brain Metabolic, Hemodynamic, and Perfusion Networks

Luoyu Wang, Yitian Tao, Qing Yang, Yan Liang, Siwei Liu, Hongcheng Shi, Dinggang Shen, Han Zhang

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

Comments 11 pages

2406.13605 2024-09-20 cs.CY cs.AI cs.GT physics.soc-ph 62%

Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?

Nicoló Fontana, Francesco Pierri, Luca Maria Aiello

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

Comments v1: 9 pages, 8 figures, 1 table v2: 11 pages, 14 figures, 1 table. Increased number of models studied, expanded results and conclusion, added references, corrected typos

2409.08330 2024-09-18 cs.CL cs.CY cs.HC 62%

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue

Jonathan Ivey, Shivani Kumar, Jiayu Liu, Hua Shen, Sushrita Rakshit, Rohan Raju, Haotian Zhang, Aparna Ananthasubramaniam, Junghwan Kim, Bowen Yi, Dustin Wright, Abraham Israeli, Anders Giovanni Møller, Lechen Zhang, David Jurgens

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

2309.07760 2024-09-17 cs.CV cs.AI cs.LG 62%

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

Thi Minh Anh Pham, An Duc Nguyen, Cephas Svosve, Vasileios Argyriou, Georgios Tzimiropoulos

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

Comments 10 pages excluding References and Appendix

2409.08666 2024-09-16 cs.LG cs.AI 62%

Towards certifiable AI in aviation: landscape, challenges, and opportunities

Hymalai Bello, Daniel Geißler, Lala Ray, Stefan Müller-Divéky, Peter Müller, Shannon Kittrell, Mengxi Liu, Bo Zhou, Paul Lukowicz

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

2409.08561 2024-09-16 cs.CL cs.AI 62%

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding

Tianqiao Liu, Zui Chen, Zitao Liu, Mi Tian, Weiqi Luo

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

2409.05495 2024-09-10 cs.LG cs.AI 62%

Using machine learning for fault detection in lighthouse light sensors

Michael Kampouridis, Nikolaos Vastardis, George Rayment

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

2409.04481 2024-09-10 q-bio.QM cs.AI cs.LG 62%

Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials

Yizhen Zheng, Huan Yee Koh, Maddie Yang, Li Li, Lauren T. May, Geoffrey I. Webb, Shirui Pan, George Church

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

2409.02239 2024-09-06 cs.SD cs.AI cs.CL eess.AS 62%

Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR

Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai

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

Comments Accepted to IEEE SLT 2024

1. 其他安全 7978 篇

Contrastive learning of T cell receptor representations

A Timeline and Analysis for Representation Plasticity in Large Language Models

Improving Emotion Recognition Accuracy with Personalized Clustering

A Two-Stage Proactive Dialogue Generator for Efficient Clinical Information Collection Using Large Language Model

Efficient Streaming LLM for Speech Recognition

Remaining Useful Life Prediction: A Study on Multidimensional Industrial Signal Processing and Efficient Transfer Learning Based on Large Language Models

SSDM: Scalable Speech Dysfluency Modeling

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Instruction Tuning With Loss Over Instructions

Agent-Driven Large Language Models for Mandarin Lyric Generation

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations

Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

E2CL: Exploration-based Error Correction Learning for Embodied Agents

Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing

Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT

KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation

From Deception to Detection: The Dual Roles of Large Language Models in Fake News

Explainable AI: Definition and attributes of a good explanation for health AI

Automotive innovation landscaping using LLM

Investigating Layer Importance in Large Language Models

Revolutionizing Disease Diagnosis with simultaneous functional PET/MR and Deeply Integrated Brain Metabolic, Hemodynamic, and Perfusion Networks

Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

Towards certifiable AI in aviation: landscape, challenges, and opportunities

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding

Using machine learning for fault detection in lighthouse light sensors

Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials

Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR