大模型对齐与安全

ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue

Zhangpu Li, Changhong Zou, Suxue Ma, Zhicheng Yang, Chen Du, Youbao Tang, Zhenjie Cao, Ning Zhang, Jui-Hsin Lai, Ruei-Sung Lin, Yuan Ni, Xingzhi Sun, Jing Xiao, Jieke Hou, Kai Zhang, Mei Han

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

FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction

Hangyu Wang, Jianghao Lin, Xiangyang Li, Bo Chen, Chenxu Zhu, Ruiming Tang, Weinan Zhang, Yong Yu

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

Comments Accepted by RecSys 2024

ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map

Yilin Ye, Shishi Xiao, Xingchen Zeng, Wei Zeng

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

Comments VIS 2024

Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training

M. Emre Sahin, Benjamin C. B. Symons, Pushpak Pati, Fayyaz Minhas, Declan Millar, Maria Gabrani, Stefano Mensa, Jan Lukas Robertus

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

Comments Paper as accepted on Quantum on 2024-09-18. The method showcased in this work is also available as a Jupyter notebook at https://github.com/qiskit-community/qiskit-machine-learning/tree/IEEE2024

Journal ref Quantum 8, 1502 (2024)

MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation

Yusheng Liao, Shuyang Jiang, Zhe Chen, Yanfeng Wang, Yu Wang

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

Comments EMNLP2024 Findings

Enhance Graph Alignment for Large Language Models

Haitong Luo, Xuying Meng, Suhang Wang, Tianxiang Zhao, Fali Wang, Hanyun Cao, Yujun Zhang

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

Comments Under review

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Huayu Chen, Hang Su, Peize Sun, Jun Zhu

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

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Siyu Zhou, Tianyi Zhou, Yijun Yang, Guodong Long, Deheng Ye, Jing Jiang, Chengqi Zhang

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

Comments 35 pages, including references and appendix. Code is available at https://github.com/elated-sawyer/WALL-E

ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation

Siyou Li, Beining Xu, Yihao Luo, Dong Nie, Le Zhang

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

An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution Alignment

Hugo Malard, Michel Olvera, Stéphane Lathuiliere, Slim Essid

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

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment

Orgest Xhelili, Yihong Liu, Hinrich Schütze

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

Comments EMNLP 2024 Findings

Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals

Yupei Wang, Renfen Hu, Zhe Zhao

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

Recurrent Alignment with Hard Attention for Hierarchical Text Rating

Chenxi Lin, Jiayu Ren, Guoxiu He, Zhuoren Jiang, Haiyan Yu, Xiaomin Zhu

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

Comments Accepted by EMNLP 2024 Main Conference

Improving Distribution Alignment with Diversity-based Sampling

Andrea Napoli, Paul White

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

Comments DCASE 2024

Long-range gene expression prediction with token alignment of large language model

Edouardo Honig, Huixin Zhan, Ying Nian Wu, Zijun Frank Zhang

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

Comments 14 pages, 10 figures

Concept Space Alignment in Multilingual LLMs

Qiwei Peng, Anders Søgaard

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

Comments EMNLP 2024

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Wenwen Zhuang, Xin Huang, Xiantao Zhang, Jin Zeng

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

EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning

Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Xiaojun Wan

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

ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable

Yuan Yin, Pegah Khayatan, Éloi Zablocki, Alexandre Boulch, Matthieu Cord

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

Comments Accepted to ECCV 2024 W-CODA Workshop

Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces

Zhiling Chen, Hanning Chen, Mohsen Imani, Ruimin Chen, Farhad Imani

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

Comments 20 pages, 7 figures

Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review

Tita A. Bach, Jenny K. Kristiansen, Aleksandar Babic, Alon Jacovi

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

Comments Accepted for publication in IEEE Access

Journal ref Access-2024-19782

Impact of Decoding Methods on Human Alignment of Conversational LLMs

Shaz Furniturewala, Kokil Jaidka, Yashvardhan Sharma

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

Enhancing Peak Assignment in 13C NMR Spectroscopy: A Novel Approach Using Multimodal Alignment

Hao Xu, Zhengyang Zhou, Pengyu Hong

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

The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication

Tom Kouwenhoven, Max Peeperkorn, Bram van Dijk, Tessa Verhoef

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

Comments Appeared at the 13th edition of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2024)

Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity Recognition

Ke Bao, Chonghuan Yang

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

Comments 9 pages, 4 figures

Towards Complex Ontology Alignment using Large Language Models

Reihaneh Amini, Sanaz Saki Norouzi, Pascal Hitzler, Reza Amini

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

AI Control: Improving Safety Despite Intentional Subversion

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger

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

Comments Edit: Fix minor typos, clarify abstract, add glossary, expand related work. ICML version: https://openreview.net/pdf?id=KviM5k8pcP

Automated Road Safety: Enhancing Sign and Surface Damage Detection with AI

Davide Merolla, Vittorio Latorre, Antonio Salis, Gianluca Boanelli

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

Comments 16 pages, 10 figures

Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach

Sojung Lucia Kim, Taehong Jang, Joonmo Ahn

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

Comments ACL2024 submitted

MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation

Zihao Wang, Haoxuan Liu, Jiaxing Yu, Tao Zhang, Yan Liu, Kejun Zhang

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

Comments 19 pages, 5 figures