大模型对齐与安全

On Fairness of Unified Multimodal Large Language Model for Image Generation

Ming Liu, Hao Chen, Jindong Wang, Liwen Wang, Bhiksha Raj Ramakrishnan, Wensheng Zhang

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

TOAST Framework: A Multidimensional Approach to Ethical and Sustainable AI Integration in Organizations

Dian Tjondronegoro

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.AI、cs.CY

Comments 25 pages, 1 figure

Sycophancy in Large Language Models: Causes and Mitigations

Lars Malmqvist

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Journal ref Computing Conference 2025 (upcoming)

Collapsed Language Models Promote Fairness

Jingxuan Xu, Wuyang Chen, Linyi Li, Yao Zhao, Yunchao Wei

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.CY

Comments ICLR 2025

Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models

Yuxuan Li, Hirokazu Shirado, Sauvik Das

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Responsible AI Question Bank: A Comprehensive Tool for AI Risk Assessment

Sung Une Lee, Harsha Perera, Yue Liu, Boming Xia, Qinghua Lu, Liming Zhu, Olivier Salvado, Jon Whittle

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.AI、cs.CY

Comments 30 pages, 6 tables, 14 figures

Developing an Ontology for AI Act Fundamental Rights Impact Assessments

Tytti Rintamaki, Harshvardhan J. Pandit

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

Comments Presented at CLAIRvoyant (ConventicLE on Artificial Intelligence Regulation) Workshop 2024

Towards an Environmental Ethics of Artificial Intelligence

Nynke van Uffelen, Lode Lauwaert, Mark Coeckelbergh, Olya Kudina

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

A Blockchain-Enabled Approach to Cross-Border Compliance and Trust

Vikram Kulothungan

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.AI、cs.CY

Comments This is a preprint of paper that has been accepted for Publication at 2024 IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications

INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models

Di Jin, Xing Liu, Yu Liu, Jia Qing Yap, Andrea Wong, Adriana Crespo, Qi Lin, Zhiyuan Yin, Qiang Yan, Ryan Ye

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.AI、cs.CY

Comments Di Jin and Xing Liu contributed equally to this work

Driving Towards Inclusion: A Systematic Review of AI-powered Accessibility Enhancements for People with Disability in Autonomous Vehicles

Ashish Bastola, Hao Wang, Sayed Pedram Haeri Boroujeni, Julian Brinkley, Ata Jahangir Moshayedi, Abolfazl Razi

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design

Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta, Venkataramana Runkana

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.LG

Designing Domain-Specific Large Language Models: The Critical Role of Fine-Tuning in Public Opinion Simulation

Haocheng Lin

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Multi-Agent Deep Reinforcement Learning for Distributed and Autonomous Platoon Coordination via Speed-regulation over Large-scale Transportation Networks

Dixiao Wei, Peng Yi, Jinlong Lei, Xingyi Zhu

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.LG

LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics

Mijntje Meijer, Hadi Mohammadi, Ayoub Bagheri

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics

Azmine Toushik Wasi, Mst Rafia Islam

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.CL、cs.CY

Comments 10 Page, 3 Figures. Accepted in: (i) ICML'24: LLMs & Cognition Workshop (Non-archival; OpenReview: https://openreview.net/forum?id=63C9YSc77p) (ii) EMNLP'24 : NLP for Science Workshop (Archival; ACL Anthology: https://aclanthology.org/2024.nlp4science-1.22/)

Journal ref Proceedings of the 1st Workshop on NLP for Science (NLP4Science), EMNLP 2024

Gender Bias in LLM-generated Interview Responses

Haein Kong, Yongsu Ahn, Sangyub Lee, Yunho Maeng

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted to NeurlIPS 2024, SoLaR workshop

On the Relationship between Truth and Political Bias in Language Models

Suyash Fulay, William Brannon, Shrestha Mohanty, Cassandra Overney, Elinor Poole-Dayan, Deb Roy, Jad Kabbara

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024

Journal ref Proc. EMNLP (2024) 9004-9018

How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law

Benjamin Fresz, Elena Dubovitskaya, Danilo Brajovic, Marco Huber, Christian Horz

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

Journal ref Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (2024), 7(1), 438-450

AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data

Qinchen Yang, Zhiqing Hong, Dongjiang Cao, Haotian Wang, Zejun Xie, Tian He, Yunhuai Liu, Yu Yang, Desheng Zhang

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted by KDD'25 ADS Track

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation

Peter Barnett, Lisa Thiergart

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

AI-Driven Human-Autonomy Teaming in Tactical Operations: Proposed Framework, Challenges, and Future Directions

Desta Haileselassie Hagos, Hassan El Alami, Danda B. Rawat

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

Comments Submitted for review to the Proceedings of the IEEE

Beyond Keywords: A Context-based Hybrid Approach to Mining Ethical Concern-related App Reviews

Aakash Sorathiya, Gouri Ginde

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.CL、cs.AI

Fairness Without Harm: An Influence-Guided Active Sampling Approach

Jinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.LG

Learning Human-like Representations to Enable Learning Human Values

Andrea Wynn, Ilia Sucholutsky, Thomas L. Griffiths

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2024

Policy Aggregation

Parand A. Alamdari, Soroush Ebadian, Ariel D. Procaccia

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.AI、cs.LG

SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents

Dawei Li, Zhen Tan, Peijia Qian, Yifan Li, Kumar Satvik Chaudhary, Lijie Hu, Jiayi Shen

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Under Review

Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?

Virgile Rennard, Christos Xypolopoulos, Michalis Vazirgiannis

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.CL、cs.AI

Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US

Jon Chun, Christian Schroeder de Witt, Katherine Elkins

专题命中 AI治理与伦理 ：safety(abstract)；分类 cs.AI、cs.CY

Comments 36 pages, 11 figures and tables

Trust or Bust: Ensuring Trustworthiness in Autonomous Weapon Systems

Kasper Cools, Clara Maathuis

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.AI、cs.CY

Comments Accepted as a workshop paper at MILCOM 2024, 8 pages