大模型对齐与安全

MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception

Yuhao Wang, Yusheng Liao, Heyang Liu, Hongcheng Liu, Yu Wang, Yanfeng Wang

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

Hard Cases Detection in Motion Prediction by Vision-Language Foundation Models

Yi Yang, Qingwen Zhang, Kei Ikemura, Nazre Batool, John Folkesson

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments IEEE Intelligent Vehicles Symposium (IV) 2024

Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers

Fan Shi, Chong Zhang, Takahiro Miki, Joonho Lee, Marco Hutter, Stelian Coros

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments RSS 2024

BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation

Chen Wang, Minpeng Liao, Zhongqiang Huang, Jiajun Zhang

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

Interpretability of Statistical, Machine Learning, and Deep Learning Models for Landslide Susceptibility Mapping in Three Gorges Reservoir Area

Cheng Chen, Lei Fan

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

A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry

Yining Huang, Keke Tang, Meilian Chen, Boyuan Wang

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

Comments 42 pages, 1 figure

Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation

Ge Qu, Jinyang Li, Bowen Li, Bowen Qin, Nan Huo, Chenhao Ma, Reynold Cheng

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

Comments Accepted to ACL Findings 2024

Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution

Xinze Li, Yixin Cao, Liangming Pan, Yubo Ma, Aixin Sun

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

Comments acl findings 2024

Pragmatic auditing: a pilot-driven approach for auditing Machine Learning systems

Djalel Benbouzid, Christiane Plociennik, Laura Lucaj, Mihai Maftei, Iris Merget, Aljoscha Burchardt, Marc P. Hauer, Abdeldjallil Naceri, Patrick van der Smagt

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

LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations

Rebeka Tóth, Tamas Bisztray, László Erdodi

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

SI-SD: Sleep Interpreter through awake-guided cross-subject Semantic Decoding

Hui Zheng, Zhong-Tao Chen, Hai-Teng Wang, Jian-Yang Zhou, Lin Zheng, Pei-Yang Lin, Yun-Zhe Liu

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

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

Rima Hazra, Sayan Layek, Somnath Banerjee, Soujanya Poria

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments Accepted at ACL 2024

A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems

Lixi Zhu, Xiaowen Huang, Jitao Sang

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

Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Models

Andrii Tytarenko

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

From Prompt Engineering to Prompt Science With Human in the Loop

Chirag Shah

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

On the Definition of Appropriate Trust and the Tools that Come with it

Helena Löfström

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

Comments 8 pages, 3 figures, Conference: ICDATA 2023

Journal ref 2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE)

TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness

Danna Zheng, Danyang Liu, Mirella Lapata, Jeff Z. Pan

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

Explainable Interface for Human-Autonomy Teaming: A Survey

Xiangqi Kong, Yang Xing, Antonios Tsourdos, Ziyue Wang, Weisi Guo, Adolfo Perrusquia, Andreas Wikander

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 45 pages, 9 figures

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response

Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze

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

Comments preprint

Self-Supervised Learning for Interventional Image Analytics: Towards Robust Device Trackers

Saahil Islam, Venkatesh N. Murthy, Dominik Neumann, Badhan Kumar Das, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C. Ghesu

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Terrain characterisation for online adaptability of automated sonar processing: Lessons learnt from operationally applying ATR to sidescan sonar in MCM applications

Thomas Guerneve, Stephanos Loizou, Andrea Munafo, Pierre-Yves Mignotte

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

Comments Presented at UACE (Underwater Acoustics Conference & Exhibition) 2023, Kalamata, Greece

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations

Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 39 pages (8 pages manuscript, 3 pages references, 28 pages appendix)

Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management

Shuochen Bi, Wenqing Bao

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 6 pages, 1 figure, 2 tables

Journal ref International Journal of Global Economics and Management ISSN: 3005-9690 (Print), ISSN: 3005-8090 (Online) | Volume 2, Number 3, Year 2024

On the Road to Clarity: Exploring Explainable AI for World Models in a Driver Assistance System

Mohamed Roshdi, Julian Petzold, Mostafa Wahby, Hussein Ebrahim, Mladen Berekovic, Heiko Hamann

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments 8 pages, 6 figures, to be published in IEEE CAI 2024

SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents

Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi, Maarten Sap, Graham Neubig, Yonatan Bisk, Hao Zhu

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Collision Avoidance Verification of Multiagent Systems with Learned Policies

Zihao Dong, Shayegan Omidshafiei, Michael Everett

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments 6 pages, 6 figures

WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction

Augustin Toma, Ronald Xie, Steven Palayew, Patrick R. Lawler, Bo Wang

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples

Dren Fazlija, Arkadij Orlov, Johanna Schrader, Monty-Maximilian Zühlke, Michael Rohs, Daniel Kudenko

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 3 pages, 3 figures, AAAI 2024 Spring Symposium on User-Aligned Assessment of Adaptive AI Systems

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences

Shreya Shankar, J. D. Zamfirescu-Pereira, Björn Hartmann, Aditya G. Parameswaran, Ian Arawjo

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

Comments 16 pages, 4 figures, 2 tables

Visualization for Trust in Machine Learning Revisited: The State of the Field in 2023

Angelos Chatzimparmpas, Kostiantyn Kucher, Andreas Kerren

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

Comments This manuscript is accepted for publication in the IEEE Computer Graphics and Applications Journal (IEEE CG&A)