大模型对齐与安全 - arXivDaily 专题

2311.11262 2023-11-21 cs.LG physics.comp-ph 57%

Uncertainty quantification for noisy inputs-outputs in physics-informed neural networks and neural operators

Zongren Zou, Xuhui Meng, George Em Karniadakis

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

2311.05417 2023-11-17 cs.LG cs.RO 57%

Predicting the Position Uncertainty at the Time of Closest Approach with Diffusion Models

Marta Guimarães, Cláudia Soares, Chiara Manfletti

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

2311.09145 2023-11-16 cs.LG stat.ML 57%

Model Agnostic Explainable Selective Regression via Uncertainty Estimation

Andrea Pugnana, Carlos Mougan, Dan Saattrup Nielsen

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

2305.14332 2023-11-16 cs.CL 57%

Evaluating and Modeling Attribution for Cross-Lingual Question Answering

Benjamin Muller, John Wieting, Jonathan H. Clark, Tom Kwiatkowski, Sebastian Ruder, Livio Baldini Soares, Roee Aharoni, Jonathan Herzig, Xinyi Wang

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.CL

Comments Published as a long paper at EMNLP 2023

2311.02243 2023-11-07 cs.LG 57%

Equal Opportunity of Coverage in Fair Regression

Fangxin Wang, Lu Cheng, Ruocheng Guo, Kay Liu, Philip S. Yu

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

Comments Accepted to NeurIPS 2023 main conference

2311.01106 2023-11-03 cs.LG 57%

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Yuzhou Cao, Hussein Mozannar, Lei Feng, Hongxin Wei, Bo An

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

Comments NeurIPS 2023

2310.19626 2023-10-31 cs.AI 57%

Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities

Zhengliang Liu, Yiwei Li, Qian Cao, Junwen Chen, Tianze Yang, Zihao Wu, John Hale, John Gibbs, Khaled Rasheed, Ninghao Liu, Gengchen Mai, Tianming Liu

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

2310.13544 2023-10-23 cs.CL cs.HC 57%

A Diachronic Perspective on User Trust in AI under Uncertainty

Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady, Mrinmaya Sachan

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.CL

Comments EMNLP 2023, 14 pages (8+6)

2310.08027 2023-10-13 cs.CL cs.CV 57%

Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection

Yi Dai, Hao Lang, Kaisheng Zeng, Fei Huang, Yongbin Li

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.CL

Comments EMNLP2023 Findings Long Paper

2309.16436 2023-09-29 cs.AI cs.LO 57%

Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving

Sumit Kumar Jha, Susmit Jha, Patrick Lincoln, Nathaniel D. Bastian, Alvaro Velasquez, Rickard Ewetz, Sandeep Neema

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

Comments 25 pages, 7 figures

2308.15231 2023-08-30 cs.CL cs.HC 57%

Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering

Angus Addlesee, Weronika Sieińska, Nancie Gunson, Daniel Hernández Garcia, Christian Dondrup, Oliver Lemon

专题命中幻觉与事实性：safety(abstract)；分类 cs.CL

Comments Accepted and will appear in the Proceedings of SIGdial 2023

2308.15141 2023-08-30 eess.IV cs.CV cs.LG 57%

Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images

Tareen Dawood, Chen Chen, Baldeep S. Sidhua, Bram Ruijsink, Justin Goulda, Bradley Porter, Mark K. Elliott, Vishal Mehta, Christopher A. Rinaldi, Esther Puyol-Anton, Reza Razavi, Andrew P. King

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

2308.14846 2023-08-30 cs.HC cs.AI cs.RO 57%

Trust in Construction AI-Powered Collaborative Robots: A Qualitative Empirical Analysis

Newsha Emaminejad, Reza Akhavian, Ph. D

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.AI

Comments 2023 ASCE International Conference on Computing in Civil Engineering (I3CE)

2301.05763 2023-08-28 cs.LG 57%

A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows

Line Pouchard, Kristofer G. Reyes, Francis J. Alexander, Byung-Jun Yoon

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

2308.02765 2023-08-08 eess.SY cs.AI cs.SY 57%

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control

Runze Lin, Yangyang Luo, Xialai Wu, Junghui Chen, Biao Huang, Lei Xie, Hongye Su

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

2205.10060 2023-07-21 cs.LG cs.NE stat.ML 57%

The Unreasonable Effectiveness of Deep Evidential Regression

Nis Meinert, Jakob Gawlikowski, Alexander Lavin

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

Comments 11 pages, 25 figures

Journal ref AAAI, vol. 37, no. 8, pp. 9134-9142, Jun. 2023

2307.05519 2023-07-13 q-bio.QM cs.AI cs.CV eess.IV 57%

Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosis

Xiaoyi Ji, Richard Salmon, Nita Mulliqi, Umair Khan, Yinxi Wang, Anders Blilie, Henrik Olsson, Bodil Ginnerup Pedersen, Karina Dalsgaard Sørensen, Benedicte Parm Ulhøi, Svein R Kjosavik, Emilius AM Janssen, Mattias Rantalainen, Lars Egevad, Pekka Ruusuvuori, Martin Eklund, Kimmo Kartasalo

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

2307.02367 2023-07-06 cs.LG physics.acc-ph 57%

Distance Preserving Machine Learning for Uncertainty Aware Accelerator Capacitance Predictions

Steven Goldenberg, Malachi Schram, Kishansingh Rajput, Thomas Britton, Chris Pappas, Dan Lu, Jared Walden, Majdi I. Radaideh, Sarah Cousineau, Sudarshan Harave

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

2306.15887 2023-06-29 cs.AI 57%

Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5

Salmonn Talebi, Elizabeth Tong, Mohammad R. K. Mofrad

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

2306.08891 2023-06-16 cs.CL 57%

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Zihui Gu, Ju Fan, Nan Tang, Songyue Zhang, Yuxin Zhang, Zui Chen, Lei Cao, Guoliang Li, Sam Madden, Xiaoyong Du

专题命中幻觉与事实性：alignment(abstract)；分类 cs.CL

Comments Working in progress

2306.07171 2023-06-13 cs.LG cs.DB 57%

Shapley Value on Probabilistic Classifiers

Xiang Li, Haocheng Xia, Jinfei Liu

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

2306.04663 2023-06-09 eess.SP cs.LG 57%

U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging

Elisabeth R. M. Heremans, Nabeel Seedat, Bertien Buyse, Dries Testelmans, Mihaela van der Schaar, Maarten De Vos

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

2305.14872 2023-06-01 cs.LG cs.SE 57%

Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning

Janek Groß, Michael Kläs, Lisa Jöckel, Pascal Gerber

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

Comments 8 pages, 7 figures, VERDI workshop collocated with the DSN conference 2023

2210.12760 2023-05-24 cs.LG 57%

On double-descent in uncertainty quantification in overparametrized models

Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

Journal ref Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (2023), PMLR 206:7089-7125

2304.11633 2023-04-25 cs.CL 57%

Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness

Bo Li, Gexiang Fang, Yang Yang, Quansen Wang, Wei Ye, Wen Zhao, Shikun Zhang

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.CL

2303.16866 2023-03-30 cs.LG cs.CV 57%

ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation

Wei Wei, Jiahuan Zhou, Hongze Li, Ying Wu

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

Comments 10 pages, 5 figures

2303.04340 2023-03-09 cs.LG cs.CV cs.DC cs.RO 57%

Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehicles

Muzi Peng, Jiangwei Wang, Dongjin Song, Fei Miao, Lili Su

专题命中幻觉与事实性：safety(abstract)；分类 cs.LG

2202.01840 2023-02-22 cs.LG 57%

Hidden Heterogeneity: When to Choose Similarity-Based Calibration

Kiri L. Wagstaff, Thomas G. Dietterich

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

Comments 22 pages, 8 figures

Journal ref Transactions on Machine Learning Research, January 2023

2210.09150 2023-02-16 cs.CL 57%

Prompting GPT-3 To Be Reliable

Chenglei Si, Zhe Gan, Zhengyuan Yang, Shuohang Wang, Jianfeng Wang, Jordan Boyd-Graber, Lijuan Wang

专题命中幻觉与事实性：safety(abstract)；分类 cs.CL

Comments ICLR 2023

2302.02595 2023-02-07 cs.LG 57%

Clarifying Trust of Materials Property Predictions using Neural Networks with Distribution-Specific Uncertainty Quantification

Cameron Gruich, Varun Madhavan, Yixin Wang, Bryan Goldsmith

专题命中幻觉与事实性：trustworthy(abstract)；分类 cs.LG

Comments 28 pages, 16 figures (8 main text, 8 SI), submitted to Machine Learning: Science & Technology journal (MLST, IOP)

1. 幻觉与事实性 1738 篇

Uncertainty quantification for noisy inputs-outputs in physics-informed neural networks and neural operators

Predicting the Position Uncertainty at the Time of Closest Approach with Diffusion Models

Model Agnostic Explainable Selective Regression via Uncertainty Estimation

Evaluating and Modeling Attribution for Cross-Lingual Question Answering

Equal Opportunity of Coverage in Fair Regression

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities

A Diachronic Perspective on User Trust in AI under Uncertainty

Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection

Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving

Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering

Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images

Trust in Construction AI-Powered Collaborative Robots: A Qualitative Empirical Analysis

A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control

The Unreasonable Effectiveness of Deep Evidential Regression

Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosis

Distance Preserving Machine Learning for Uncertainty Aware Accelerator Capacitance Predictions

Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Shapley Value on Probabilistic Classifiers

U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging

Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning

On double-descent in uncertainty quantification in overparametrized models

Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness

ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation

Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehicles

Hidden Heterogeneity: When to Choose Similarity-Based Calibration

Prompting GPT-3 To Be Reliable

Clarifying Trust of Materials Property Predictions using Neural Networks with Distribution-Specific Uncertainty Quantification