大模型对齐与安全

Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources

Hannah-Beth Clark, Margaux Dowland, Laura Benton, Reka Budai, Ibrahim Kaan Keskin, Emma Searle, Matthew Gregory, Mark Hodierne, William Gayne, John Roberts

专题命中 安全评测 ：safety(title)；alignment(abstract)；分类 cs.AI、cs.CY

Comments 27 pages, Part of MIT Open Learning AI and Open Education Initiative Series, published Jan 2025 https://aiopeneducation.pubpub.org/pub/i36sncz8/release/3?readingCollection=06969c6d

A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks

Hieu Minh "Jord" Nguyen

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL、cs.AI

Comments Advancing Artificial Intelligence through Theory of Mind Workshop, AAAI 2025

Entity Alignment with Noisy Annotations from Large Language Models

Shengyuan Chen, Qinggang Zhang, Junnan Dong, Wen Hua, Qing Li, Xiao Huang

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Journal ref NeurIPS 2024

Linear Alignment of Vision-language Models for Image Captioning

Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.LG

Comments 9 pages (+ references and appendix)

Advancing Trustworthy AI for Sustainable Development: Recommendations for Standardising AI Incident Reporting

Avinash Agarwal, Manisha J Nene

专题命中 安全评测 ：trustworthy(title,abstract)；分类 cs.AI、cs.CY

Comments 8 pages, 10 tables, and 1 figure. Accepted at the International Telecommunication Union (ITU) Kaleidoscope 2024

Journal ref 2024 ITU Kaleidoscope: Innovation and Digital Transformation for a Sustainable World (ITU K), New Delhi, India, 2024, pp. 1-8

Revisiting CLIP: Efficient Alignment of 3D MRI and Tabular Data using Domain-Specific Foundation Models

Jakob Krogh Petersen, Valdemar Licht, Mads Nielsen, Asbjørn Munk

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 2 figures. To be published in ISBI 2025

EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union

Brian Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen, Alois Knoll

专题命中 安全评测 ：safety(title,abstract)；分类 cs.AI、cs.LG

Comments 8 pages (IEEE double column format), 7 figures, 2 tables

Baichuan Alignment Technical Report

Mingan Lin, Fan Yang, Yanjun Shen, Haoze Sun, Tianpeng Li, Tao Zhang, Chenzheng Zhu, Tao Zhang, Miao Zheng, Xu Li, Yijie Zhou, Mingyang Chen, Yanzhao Qin, Youquan Li, Hao Liang, Fei Li, Yadong Li, Mang Wang, Guosheng Dong, Kun Fang, Jianhua Xu, Bin Cui, Wentao Zhang, Zenan Zhou, Weipeng Chen

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.LG

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models

Yingshui Tan, Boren Zheng, Baihui Zheng, Kerui Cao, Huiyun Jing, Jincheng Wei, Jiaheng Liu, Yancheng He, Wenbo Su, Xiangyong Zhu, Bo Zheng, Kaifu Zhang

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL、cs.AI

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

Shaolei Zhang, Kehao Zhang, Qingkai Fang, Shoutao Guo, Yan Zhou, Xiaodong Liu, Yang Feng

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments BayLing 2's online demo: http://nlp.ict.ac.cn/bayling/demo. BayLing 2's code and models: https://github.com/ictnlp/BayLing

The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap

Yedi Zhang, Yufan Cai, Xinyue Zuo, Xiaokun Luan, Kailong Wang, Zhe Hou, Yifan Zhang, Zhiyuan Wei, Meng Sun, Jun Sun, Jing Sun, Jin Song Dong

专题命中 安全评测 ：trustworthy(title,abstract)；分类 cs.CL、cs.AI

Comments 24 pages, 4 figures

Quantized Delta Weight Is Safety Keeper

Yule Liu, Zhen Sun, Xinlei He, Xinyi Huang

专题命中 安全评测 ：safety(title)；alignment(abstract)；分类 cs.AI、cs.LG

ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain

Haochen Zhao, Xiangru Tang, Ziran Yang, Xiao Han, Xuanzhi Feng, Yueqing Fan, Senhao Cheng, Di Jin, Yilun Zhao, Arman Cohan, Mark Gerstein

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL、cs.AI

Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness

Shayan Alipour, Indira Sen, Mattia Samory, Tanushree Mitra

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.CY

Benchmarking Distributional Alignment of Large Language Models

Nicole Meister, Carlos Guestrin, Tatsunori Hashimoto

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation

Jingnan Zheng, Han Wang, An Zhang, Tai D. Nguyen, Jun Sun, Tat-Seng Chua

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Journal ref 2024 Neurips

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

Xin Xiao, Bohong Wu, Jiacong Wang, Chunyuan Li, Xun Zhou, Haoyuan Guo

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments NeurlPS 2024, Camera ready

Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs

Xiaoqing Chen, Ziwei Wang, Dongrui Wu

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.AI、cs.LG

Journal ref IEEE Trans. on Neural Systems and Rehabilitation Engineering, 32:1703-1714, 2024

TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment

Wei Li, Hehe Fan, Yongkang Wong, Mohan Kankanhalli, Yi Yang

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2024 (Spotlight)

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models

Hengyi Wang, Shiwei Tan, Hao Wang

专题命中 安全评测 ：trustworthy(title,abstract)；分类 cs.AI、cs.LG

Comments Proceedings of the 41st International Conference on Machine Learning (ICML 2024)

Journal ref PMLR 235:51502-51522, 2024

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

Junda Wu, Xintong Li, Ruoyu Wang, Yu Xia, Yuxin Xiong, Jianing Wang, Tong Yu, Xiang Chen, Branislav Kveton, Lina Yao, Jingbo Shang, Julian McAuley

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.LG

Comments 10 pages

CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs

Zhihao Liu, Chenhui Hu

专题命中 安全评测 ：safety(title,abstract)；分类 cs.CL、cs.LG

Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach

Firas Bayram, Bestoun S. Ahmed

专题命中 安全评测 ：trustworthy(title,abstract)；分类 cs.AI、cs.LG

Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Data

Katarzyna Kobylińska, Mateusz Krzyziński, Rafał Machowicz, Mariusz Adamek, Przemysław Biecek

专题命中 安全评测 ：trustworthy(title,abstract)；分类 cs.AI、cs.LG

Comments This work has been submitted to the IEEE for possible publication

GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation

Junyu Luo, Yiyang Gu, Xiao Luo, Wei Ju, Zhiping Xiao, Yusheng Zhao, Jingyang Yuan, Ming Zhang

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.AI、cs.LG

Comments IEEE TPAMI

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant G Honavar

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2024 Main

Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs

Mustafa Shukor, Matthieu Cord

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2024. Code: https://github.com/mshukor/ima-lmms. Project page: https://ima-lmms.github.io/

Risk Alignment in Agentic AI Systems

Hayley Clatterbuck, Clinton Castro, Arvo Muñoz Morán

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.AI、cs.CY

Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints

Jianuo Huang

专题命中 安全评测 ：safety(title,abstract)；分类 cs.AI、cs.LG

Comments The experiment and method plan are abolished and need to be redesigned

Inference-Time Language Model Alignment via Integrated Value Guidance

Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao

专题命中 安全评测 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024 Findings