大模型对齐与安全

Enhancing Domain Adaptation through Prompt Gradient Alignment

Hoang Phan, Lam Tran, Quyen Tran, Trung Le

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments Accepted to NeurIPS 2024

LANGALIGN: Enhancing Non-English Language Models via Cross-Lingual Embedding Alignment

Jong Myoung Kim, Young-Jun Lee, Ho-Jin Choi, Sangkeun Jung

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments now preparing

LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?

Amr Keleg

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments Accepted to the C3NLP workshop (Co-located with NAACL 2025)

Efficient Multi-Task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment

Luyang Fang, Ehsan Latif, Haoran Lu, Yifan Zhou, Ping Ma, Xiaoming Zhai

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments Submitted to AIED2025

Partial Distribution Alignment via Adaptive Optimal Transport

Pei Yang, Qi Tan, Guihua Wen

专题命中 其他安全 ：alignment(title)；分类 cs.LG

How desirable is alignment between LLMs and linguistically diverse human users?

Pia Knoeferle, Sebastian Möller, Dorothea Kolossa, Veronika Solopova, Georg Rehm

专题命中 其他安全 ：alignment(title)；分类 cs.CL

LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy

Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments In Findings of NAACL 2025(The 2025 Annual Conference of the Nations of the Americas Chapter of the ACL)

Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity

Hyosoon Jang, Yunhui Jang, Jaehyung Kim, Sungsoo Ahn

专题命中 其他安全 ：alignment(title)；分类 cs.LG

SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation

Jungwoo Kim, Minsang Kim, Sungjin Lee

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments 12 pages, 12 figures

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

专题命中 其他安全 ：alignment(title)；分类 cs.LG

The Goofus & Gallant Story Corpus for Practical Value Alignment

Md Sultan Al Nahian, Tasmia Tasrin, Spencer Frazier, Mark Riedl, Brent Harrison

专题命中 其他安全 ：alignment(title)；分类 cs.AI

Comments Accepted by International Conference on Machine Learning and Applications (ICMLA) 2024. Main Conference, Long Paper

A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space

Yonghao He, Hu Su, Haiyong Yu, Cong Yang, Wei Sui, Cong Wang, Song Liu

专题命中 其他安全 ：alignment(title)；分类 cs.AI

Deep Reinforcement Learning Based Systems for Safety Critical Applications in Aerospace

Abedin Sherifi

专题命中 其他安全 ：safety(title)；分类 cs.AI

Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks

Sungkyung Kim, Adam Lee, Junyoung Park, Andrew Chung, Jusang Oh, Jay-Yoon Lee

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments EMNLP 2024 Findings

Examining the Role of Relationship Alignment in Large Language Models

Kristen M. Altenburger, Hongda Jiang, Robert E. Kraut, Yi-Chia Wang, Jane Dwivedi-Yu

专题命中 其他安全 ：alignment(title)；分类 cs.CL

X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment

Dongjae Shin, Hyeonseok Lim, Inho Won, Changsu Choi, Minjun Kim, Seungwoo Song, Hangyeol Yoo, Sangmin Kim, Kyungtae Lim

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Journal ref https://aclanthology.org/2024.findings-naacl.158

Boltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment

Sanzo Miyazawa

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments In arXiv:1909.05006v3 the values of selective temperature for protein PF00153, $T_s$ in Table 5 and in the section 2.8, and folding free energy for PF00595, and in the v4 the method for soft-thresholding were corrected; shown in red. The v2 was published in the IEEE/ACM Transactions on Computational Biology and Bioinformatics. The program is available from https://gitlab.com/sanzo.miyazawa/BM/

Journal ref IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022 Jan-Feb;19(1):328-342

GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?

Barah Fazili, Koustava Goswami, Natwar Modani, Inderjeet Nair

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Synthetic Cancer -- Augmenting Worms with LLMs

Benjamin Zimmerman, David Zollikofer

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

Comments Won first place at the Swiss AI Safety Prize. Some technical details omitted, contact authors for more information

Towards Dialogues for Joint Human-AI Reasoning and Value Alignment

Elfia Bezou-Vrakatseli, Oana Cocarascu, Sanjay Modgil

专题命中 其他安全 ：alignment(title)；分类 cs.AI

Learning Galaxy Intrinsic Alignment Correlations

Sneh Pandya, Yuanyuan Yang, Nicholas Van Alfen, Jonathan Blazek, Robin Walters

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments 15 pages, 6 figures, 1 table. Accepted at the Data-centric Machine Learning Research (DMLR) Workshop at ICLR 2024

StackGenVis: Alignment of Data, Algorithms, and Models for Stacking Ensemble Learning Using Performance Metrics

Angelos Chatzimparmpas, Rafael M. Martins, Kostiantyn Kucher, Andreas Kerren

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments This manuscript is accepted for publication in a special issue of IEEE Transactions on Visualization and Computer Graphics Journal (IEEE TVCG)

Journal ref IEEE TVCG 2021, 27(2), 1547-1557

A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment

Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Fei Huang, Yongbin Li, Nevin L. Zhang

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments LREC-Coling 2024

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models

Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments Preprint

DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models

Norman Di Palo, Edward Johns

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments To appear at 2024 IEEE International Conference on Robotics and Automation (ICRA)

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment

Utkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu, Carl Vondrick, Bharath Hariharan, Kavita Bala

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue

Aron Molnar, Jaap Jumelet, Mario Giulianelli, Arabella Sinclair

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments CoNLL 2023

Character-Level Bangla Text-to-IPA Transcription Using Transformer Architecture with Sequence Alignment

Jakir Hasan, Shrestha Datta, Ameya Debnath

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments Achieved top position with a word error rate of 0.10582 in the public ranking of DataVerse Challenge - ITVerse 2023 (link: https://www.kaggle.com/competitions/dataverse_2023/). All codes can be found on the respective competition webpage

Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models

Joseph Marvin Imperial, Harish Tayyar Madabushi

专题命中 其他安全 ：alignment(title)；分类 cs.CL

Comments Final camera-ready for EMNLP GEM Workshop 2023

Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data

Cheol Jun Cho, Edward F. Chang, Gopala K. Anumanchipalli

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments Accepted at ICML 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning (2023), PMLR 202:5661-5676