大模型对齐与安全

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

Xin Liu, Muhammad Khalifa, Lu Wang

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

Comments accepted to ICLR 2024

NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services

Yuxuan Chen, Rongpeng Li, Zhifeng Zhao, Chenghui Peng, Jianjun Wu, Ekram Hossain, Honggang Zhang

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

End-to-end Conditional Robust Optimization

Abhilash Chenreddy, Erick Delage

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

On the Out-of-Distribution Coverage of Combining Split Conformal Prediction and Bayesian Deep Learning

Paul Scemama, Ariel Kapusta

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

Comments 26 pages, 18 figures

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem

Yuhong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao

专题命中 幻觉与事实性 ：RLHF(abstract)；分类 cs.CL

Comments 11 pages, 8 figures, accepted by LREC-Coling 2024

HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs

Cem Uluoglakci, Tugba Taskaya Temizel

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

Comments EACL SRW 2024 Camera Ready

Question Calibration and Multi-Hop Modeling for Temporal Question Answering

Chao Xue, Di Liang, Pengfei Wang, Jing Zhang

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

Comments Accepted by AAAI 2024

A Factor Graph Model of Trust for a Collaborative Multi-Agent System

Behzad Akbari, Mingfeng Yuan, Hao Wang, Haibin Zhu, Jinjun Shan

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

Assessing Uncertainty Estimation Methods for 3D Image Segmentation under Distribution Shifts

Masoumeh Javanbakhat, Md Tasnimul Hasan, Cristoph Lippert

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

Understanding the Effects of Iterative Prompting on Truthfulness

Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

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

Digital cloning of online social networks for language-sensitive agent-based modeling of misinformation spread

Prateek Puri, Gabriel Hassler, Anton Shenk, Sai Katragadda

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

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models

Junyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen

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

Comments 24 pages, 8 figures, 13 tables

Improved uncertainty quantification for neural networks with Bayesian last layer

Felix Fiedler, Sergio Lucia

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

Comments This work has been published at IEEE Access with Digital Object Identifier 10.1109/ACCESS.2023.3329685 under a Creative Commons Attribution 4.0 License

Journal ref IEEE Access, vol. 11, 2023

Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work

Rishab Jain, Aditya Jain

专题命中 幻觉与事实性 ：red teaming(abstract)；分类 cs.CY

Comments 10 pages, 6 figures

Estimating calibration error under label shift without labels

Teodora Popordanoska, Gorjan Radevski, Tinne Tuytelaars, Matthew B. Blaschko

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

Comments Preprint

Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applications

Sabine Wehnert

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

Comments 12 pages, 2 figures

An Empirical Study of Uncertainty Estimation Techniques for Detecting Drift in Data Streams

Anton Winter, Nicolas Jourdan, Tristan Wirth, Volker Knauthe, Arjan Kuijper

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

Comments NeurIPS 2023: Workshop on Distribution Shifts

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

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

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

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

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

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

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

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)

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

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

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

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

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)