大模型对齐与安全

RIRO: Reshaping Inputs, Refining Outputs Unlocking the Potential of Large Language Models in Data-Scarce Contexts

Ali Hamdi, Hozaifa Kassab, Mohamed Bahaa, Marwa Mohamed

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

Responsibility-aware Strategic Reasoning in Probabilistic Multi-Agent Systems

Chunyan Mu, Muhammad Najib, Nir Oren

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

CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning

Yiping Wang, Yifang Chen, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon Shaolei Du

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

Comments This paper supercedes our previous VAS paper (arXiv:2402.02055). It's accepted by NeurIPS2024 as spotlight paper. DataComp benchmark: https://www.datacomp.ai/dcclip/leaderboard.html

Benchmarking Harmonized Tariff Schedule Classification Models

Bryce Judy

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

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

Guangsheng Bao, Yanbin Zhao, Zhiyang Teng, Linyi Yang, Yue Zhang

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

Comments ICLR 2024 camera version (9 pages, 5 figures, 11 tables)

GPTDrawer: Enhancing Visual Synthesis through ChatGPT

Kun Li, Xinwei Chen, Tianyou Song, Hansong Zhang, Wenzhe Zhang, Qing Shan

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

Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language

Anastasia Zhukova, Christian E. Matt, Bela Gipp

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

Comments accepted in the First Workshop on Language Models for Low-Resource Languages (LoResLM) co-located with the 31st International Conference on Computational Linguistics (COLING 2025)

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

Jianhui Pang, Fanghua Ye, Longyue Wang, Dian Yu, Derek F. Wong, Shuming Shi, Zhaopeng Tu

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

Comments This paper has been accepted by TACL; A pre-MIT Press publication version; Longyue Wang is the Corresponding Author

Disentangling Mean Embeddings for Better Diagnostics of Image Generators

Sebastian G. Gruber, Pascal Tobias Ziegler, Florian Buettner

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

Comments Published at Interpretable AI: Past, Present and Future Workshop at NeurIPS 2024

Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control

Arthur Müller, Vishal Rangras, Georg Schnittker, Michael Waldmann, Maxim Friesen, Tobias Ferfers, Lukas Schreckenberg, Florian Hufen, Jürgen Jasperneite, Marco Wiering

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments Paper was accepted by ICMLA 2021 (20th IEEE International Conference on Machine Learning and Applications). Code available under https://github.com/RL-INA/LemgoRL

The AI Interface: Designing for the Ideal Machine-Human Experience (Editorial)

Aparna Sundar, Tony Russell-Rose, Udo Kruschwitz, Karen Machleit

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

Comments 8 pages

Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning

Mateo Alejandro Rojas, Rafael Carranza

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

LinVT: Empower Your Image-level Large Language Model to Understand Videos

Lishuai Gao, Yujie Zhong, Yingsen Zeng, Haoxian Tan, Dengjie Li, Zheng Zhao

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

Representation Learning of Multivariate Time Series using Attention and Adversarial Training

Leon Scharwächter, Sebastian Otte

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

Representation Learning with Large Language Models for Recommendation

Xubin Ren, Wei Wei, Lianghao Xia, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, Chao Huang

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

Comments Published as a WWW'24 full paper

Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations

Michael Zhang, Nimit S. Sohoni, Hongyang R. Zhang, Chelsea Finn, Christopher Ré

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

Comments 38 pages, 14 figures. ICML 2022 Long Talk

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective

Van-Cuong Pham, Thien Huu Nguyen

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments EMNLP 2024

Cognitive Architecture Toward Common Ground Sharing Among Humans and Generative AIs: Trial on Model-Model Interactions in Tangram Naming Task

Junya Morita, Tatsuya Yui, Takeru Amaya, Ryuichiro Higashinaka, Yugo Takeuchi

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

Comments Proceedings of the 2023 AAAI Fall Symposium on Integrating Cognitive Architectures and Generative Models

Journal ref Proceedings of the 2023 AAAI Fall Symposia, vol.2, no. 1, 2023

Considerations Influencing Offense-Defense Dynamics From Artificial Intelligence

Giulio Corsi, Kyle Kilian, Richard Mallah

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

Seungone Kim, Juyoung Suk, Shayne Longpre, Bill Yuchen Lin, Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo

专题命中 安全评测 ：harmlessness(abstract)；分类 cs.CL

Comments EMNLP 2024 (Main Conference)

Soft Checksums to Flag Untrustworthy Machine Learning Surrogate Predictions and Application to Atomic Physics Simulations

Casey Lauer, Robert C. Blake, Jonathan B. Freund

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

Comments 8 pages, 3 figures

Detecting abnormal heart sound using mobile phones and on-device IConNet

Linh Vu, Thu Tran

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

Comments N2Women'24 Workshop, MobiSys 2024, Tokyo, Japan

HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Lajos Muzsai, David Imolai, András Lukács

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 16 pages, 9 figures

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages

Edward Bayes, Israel Abebe Azime, Jesujoba O. Alabi, Jonas Kgomo, Tyna Eloundou, Elizabeth Proehl, Kai Chen, Imaan Khadir, Naome A. Etori, Shamsuddeen Hassan Muhammad, Choice Mpanza, Igneciah Pocia Thete, Dietrich Klakow, David Ifeoluwa Adelani

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments working paper

Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model

Qiujing Lu, Meng Ma, Ximiao Dai, Xuanhan Wang, Shuo Feng

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Generating a Low-code Complete Workflow via Task Decomposition and RAG

Orlando Marquez Ayala, Patrice Béchard

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Under review; 12 pages, 8 figures

EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents

Zihao Zhu, Bingzhe Wu, Zhengyou Zhang, Lei Han, Qingshan Liu, Baoyuan Wu

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

PDZSeg: Adapting the Foundation Model for Dissection Zone Segmentation with Visual Prompts in Robot-assisted Endoscopic Submucosal Dissection

Mengya Xu, Wenjin Mo, Guankun Wang, Huxin Gao, An Wang, Zhen Li, Xiaoxiao Yang, Hongliang Ren

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Confidence-Aware Deep Learning for Load Plan Adjustments in the Parcel Service Industry

Thomas Bruys, Reza Zandehshahvar, Amira Hijazi, Pascal Van Hentenryck

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

Comments 16 pages, 11 figures

Just-in-Time Detection of Silent Security Patches

Xunzhu Tang, Zhenghan Chen, Kisub Kim, Haoye Tian, Saad Ezzini, Jacques Klein

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