大模型对齐与安全

Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs

Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Shirui Pan, Xindong Wu

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

From human-centered to social-centered artificial intelligence: Assessing ChatGPT's impact through disruptive events

Skyler Wang, Ned Cooper, Margaret Eby

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

Comments 14 pages. Published version

Journal ref Big Data & Society 11(1), 1-14 (2024)

Integrating Large Language Models for UAV Control in Simulated Environments: A Modular Interaction Approach

Abhishek Phadke, Alihan Hadimlioglu, Tianxing Chu, Chandra N Sekharan

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

FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning

Wei Chen, Meng Yuan, Zhao Zhang, Ruobing Xie, Fuzhen Zhuang, Deqing Wang, Rui Liu

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

Comments 12 pages, submitted to TKDE

A Survey on Knowledge Distillation of Large Language Models

Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, Tianyi Zhou

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

Comments 43 pages

Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts

Sharon Levy, William D. Adler, Tahilin Sanchez Karver, Mark Dredze, Michelle R. Kaufman

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

Comments EMNLP Findings 2024

Evaluating Gender Bias of LLMs in Making Morality Judgements

Divij Bajaj, Yuanyuan Lei, Jonathan Tong, Ruihong Huang

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

Comments Accepted by EMNLP Findings 2024

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li

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

Detecting Bias and Enhancing Diagnostic Accuracy in Large Language Models for Healthcare

Pardis Sadat Zahraei, Zahra Shakeri

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

Coordinated Disclosure of Dual-Use Capabilities: An Early Warning System for Advanced AI

Joe O'Brien, Shaun Ee, Jam Kraprayoon, Bill Anderson-Samways, Oscar Delaney, Zoe Williams

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

Comments 76 pages

Foregrounding Artist Opinions: A Survey Study on Transparency, Ownership, and Fairness in AI Generative Art

Juniper Lovato, Julia Zimmerman, Isabelle Smith, Peter Dodds, Jennifer Karson

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

Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs

Amartya Roy, Danush Khanna, Devanshu Mahapatra, Vasanthakumar, Avirup Das, Kripabandhu Ghosh

专题命中 AI治理与伦理 ：DPO(abstract)；分类 cs.CL

Comments 17 pages, 5 Figures

Socially Responsible Data for Large Multilingual Language Models

Andrew Smart, Ben Hutchinson, Lameck Mbangula Amugongo, Suzanne Dikker, Alex Zito, Amber Ebinama, Zara Wudiri, Ding Wang, Erin van Liemt, João Sedoc, Seyi Olojo, Stanley Uwakwe, Edem Wornyo, Sonja Schmer-Galunder, Jamila Smith-Loud

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

Journal ref ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization, 2024

Dataset | Mindset = Explainable AI | Interpretable AI

Caesar Wu, Rajkumar Buyya, Yuan Fang Li, Pascal Bouvry

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

Investigating Context Effects in Similarity Judgements in Large Language Models

Sagar Uprety, Amit Kumar Jaiswal, Haiming Liu, Dawei Song

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

Comments Accepted at The First Workshop on AI Behavioral Science (AIBS 2024), held in conjunction with KDD 2024

AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews

Keith Tyser, Ben Segev, Gaston Longhitano, Xin-Yu Zhang, Zachary Meeks, Jason Lee, Uday Garg, Nicholas Belsten, Avi Shporer, Madeleine Udell, Dov Te'eni, Iddo Drori

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

Comments 42 pages

Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs

Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Jiaqi Li, Aihua Pei, Zhiqiang Wang, Pengliang Ji, Haoyu Wang, Jiaqi Huo

专题命中 AI治理与伦理 ：RLHF(abstract)；分类 cs.AI

Comments The first three authors contributed equally to this work

OpenBias: Open-set Bias Detection in Text-to-Image Generative Models

Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Dejia Xu, Vidit Goel, Xingqian Xu, Zhangyang Wang, Humphrey Shi, Nicu Sebe

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

Comments CVPR 2024 Highlight - Code: https://github.com/Picsart-AI-Research/OpenBias

How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies

Alina Leidinger, Richard Rogers

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

Comments Accepted at AAAI/ACM AI, Ethics, and Society

The Sociolinguistic Foundations of Language Modeling

Jack Grieve, Sara Bartl, Matteo Fuoli, Jason Grafmiller, Weihang Huang, Alejandro Jawerbaum, Akira Murakami, Marcus Perlman, Dana Roemling, Bodo Winter

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

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?

Jingyan Zhou, Minda Hu, Junan Li, Xiaoying Zhang, Xixin Wu, Irwin King, Helen Meng

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

Journal ref Findings of the Association for Computational Linguistics: NAACL 2024

MBIAS: Mitigating Bias in Large Language Models While Retaining Context

Shaina Raza, Ananya Raval, Veronica Chatrath

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

Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias

Shan Chen, Jack Gallifant, Mingye Gao, Pedro Moreira, Nikolaj Munch, Ajay Muthukkumar, Arvind Rajan, Jaya Kolluri, Amelia Fiske, Janna Hastings, Hugo Aerts, Brian Anthony, Leo Anthony Celi, William G. La Cava, Danielle S. Bitterman

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

Comments Submitted for review, data visualization tool available at: www.crosscare.net

Crossing the principle-practice gap in AI ethics with ethical problem-solving

Nicholas Kluge Corrêa, James William Santos, Camila Galvão, Marcelo Pasetti, Dieine Schiavon, Faizah Naqvi, Robayet Hossain, Nythamar De Oliveira

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

Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting

Sagnik Mukherjee, Muhammad Farid Adilazuarda, Sunayana Sitaram, Kalika Bali, Alham Fikri Aji, Monojit Choudhury

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

Fair by design: A sociotechnical approach to justifying the fairness of AI-enabled systems across the lifecycle

Marten H. L. Kaas, Christopher Burr, Zoe Porter, Berk Ozturk, Philippa Ryan, Michael Katell, Nuala Polo, Kalle Westerling, Ibrahim Habli

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

Comments 18 pages, 2 figures

On the Maximal Local Disparity of Fairness-Aware Classifiers

Jinqiu Jin, Haoxuan Li, Fuli Feng

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

Journal ref ICML 2024

Safeguarding Large Language Models: A Survey

Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang

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

Comments under review. arXiv admin note: text overlap with arXiv:2402.01822

Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation

Anjanava Biswas, Wrick Talukdar

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

Comments 15 pages, 7 figures

Journal ref International Journal of Innovative Science and Research Technology: Vol. 9 (2024): No. 5, 994-1008

Cyber Risks of Machine Translation Critical Errors : Arabic Mental Health Tweets as a Case Study

Hadeel Saadany, Ashraf Tantawy, Constantin Orasan

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