大模型对齐与安全

Semi-supervised Fine-tuning for Large Language Models

Junyu Luo, Xiao Luo, Xiusi Chen, Zhiping Xiao, Wei Ju, Ming Zhang

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

Comments Github Repo: https://github.com/luo-junyu/SemiEvol

Journal ref NAACL 2025

Does Editing Provide Evidence for Localization?

Zihao Wang, Victor Veitch

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

Learning Generalizable Prompt for CLIP with Class Similarity Knowledge

Sehun Jung, Hyang-won Lee

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

Can LLM Agents Maintain a Persona in Discourse?

Pranav Bhandari, Nicolas Fay, Michael Wise, Amitava Datta, Stephanie Meek, Usman Naseem, Mehwish Nasim

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

A Survey of Automatic Prompt Engineering: An Optimization Perspective

Wenwu Li, Xiangfeng Wang, Wenhao Li, Bo Jin

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

Comments 19 pages, 4 figures

ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models

Shixuan Li, Wei Yang, Peiyu Zhang, Xiongye Xiao, Defu Cao, Yuehan Qin, Xiaole Zhang, Yue Zhao, Paul Bogdan

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

Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations

Luyi Ma, Xiaohan Li, Zezhong Fan, Kai Zhao, Jianpeng Xu, Jason Cho, Praveen Kanumala, Kaushiki Nag, Sushant Kumar, Kannan Achan

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

Exploring the Personality Traits of LLMs through Latent Features Steering

Shu Yang, Shenzhe Zhu, Liang Liu, Lijie Hu, Mengdi Li, Di Wang

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

Comments under review

Learning to Substitute Words with Model-based Score Ranking

Hongye Liu, Ricardo Henao

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

Comments Accepted at NAACL 2025 (main, long)

Are Large Language Models the future crowd workers of Linguistics?

Iris Ferrazzo

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

Machine Learning-Based Estimation Of Wave Direction For Unmanned Surface Vehicles

Manele Ait Habouche, Mickaël Kerboeuf, Goulven Guillou, Jean-Philippe Babau

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

Scaling FP8 training to trillion-token LLMs

Maxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry

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

Interpreting What Typical Fault Signals Look Like via Prototype-matching

Qian Chen, Xingjian Dong, Zhike Peng

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

Comments 17 pages, 12 figures, 6 tables

Journal ref Advanced Engineering Informatics, vol. 62, p. 102849, Oct. 2024

LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction

Ziwei Wang, Jie Zhou, Qin Chen, Min Zhang, Bo Jiang, Aimin Zhou, Qinchun Bai, Liang He

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

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Tao Liu, Kai Wang, Senmao Li, Joost van de Weijer, Fahad Shahbaz Khan, Shiqi Yang, Yaxing Wang, Jian Yang, Ming-Ming Cheng

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

Comments 28 pages, 22 figures, ICLR2025 conference

Hybrid LLM-DDQN based Joint Optimization of V2I Communication and Autonomous Driving

Zijiang Yan, Hao Zhou, Hina Tabassum, Xue Liu

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

Comments Accepted by IEEE Wireless Communications Letters

ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution

Kanika Goswami, Puneet Mathur, Ryan Rossi, Franck Dernoncourt

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

Time-Reversal Provides Unsupervised Feedback to LLMs

Yerram Varun, Rahul Madhavan, Sravanti Addepalli, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain

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

Comments Accepted as a spotlight in NeurIPS 2024

Journal ref The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

Wearable Accelerometer Foundation Models for Health via Knowledge Distillation

Salar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew C. Miller, Ian Shapiro

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

Comments updated format

Large Language Models for Biomedical Knowledge Graph Construction: Information extraction from EMR notes

Vahan Arsenyan, Spartak Bughdaryan, Fadi Shaya, Kent Small, Davit Shahnazaryan

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

SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments

Simon Dahan, Gabriel Bénédict, Logan Z. J. Williams, Yourong Guo, Daniel Rueckert, Robert Leech, Emma C. Robinson

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

Comments 27 pages, accepted to ICLR 2025

Optimal Signal Decomposition-based Multi-Stage Learning for Battery Health Estimation

Vijay Babu Pamshetti, Wei Zhang, King Jet Tseng, Bor Kiat Ng, Qingyu Yan

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

Comments 6 pages

CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters

Zishuo Feng, Feng Cao

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

Comments 8 pages, 5 figures, 8 tables

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable

Shreyash Arya, Sukrut Rao, Moritz Böhle, Bernt Schiele

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

Comments 31 pages, 9 figures, 12 tables, Neural Information Processing Systems (NeurIPS) 2024; added references, corrected typos

The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories

Raj Sanjay Shah, Sashank Varma

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

Control-ITRA: Controlling the Behavior of a Driving Model

Vasileios Lioutas, Adam Scibior, Matthew Niedoba, Berend Zwartsenberg, Frank Wood

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

Comments 16 pages, 2 figures

Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models

Hui-Po Wang, Mario Fritz

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

Comments camera-ready in NeurIPS 2024

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

An Yan, Zhengyuan Yang, Junda Wu, Wanrong Zhu, Jianwei Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Julian McAuley, Jianfeng Gao, Lijuan Wang

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

Comments published at COLM-2024

Frontier Models are Capable of In-context Scheming

Alexander Meinke, Bronson Schoen, Jérémy Scheurer, Mikita Balesni, Rusheb Shah, Marius Hobbhahn

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

Noise-powered Multi-modal Knowledge Graph Representation Framework

Zhuo Chen, Yin Fang, Yichi Zhang, Lingbing Guo, Jiaoyan Chen, Jeff Z. Pan, Huajun Chen, Wen Zhang

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

Comments COLING 2025 Accepted, Repo is available at https://github.com/zjukg/SNAG