大模型对齐与安全

Enhancing Diagnostic Reliability of Foundation Model with Uncertainty Estimation in OCT Images

Yuanyuan Peng, Aidi Lin, Meng Wang, Tian Lin, Ke Zou, Yinglin Cheng, Tingkun Shi, Xulong Liao, Lixia Feng, Zhen Liang, Xinjian Chen, Huazhu Fu, Haoyu Chen

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

Comments All codes are available at https://github.com/yuanyuanpeng0129/FMUE

Deepfake tweets automatic detection

Adam Frej, Adrian Kaminski, Piotr Marciniak, Szymon Szmajdzinski, Soveatin Kuntur, Anna Wroblewska

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

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA

Zehuan Zhang, Hongxiang Fan, Hao Mark Chen, Lukasz Dudziak, Wayne Luk

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

Comments Design Automation Conference (DAC) 2024

Are Logistic Models Really Interpretable?

Danial Dervovic, Freddy Lécué, Nicolás Marchesotti, Daniele Magazzeni

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

Comments 36 pages, 5 Figures. Extended version of paper accepted to IJCAI 2024. arXiv admin note: substantial text overlap with arXiv:2211.06360

Improving Multi-Agent Debate with Sparse Communication Topology

Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, Eugene Ie

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

Comments 13 pages, 9 figures

Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs

Shang Zhou, Feng Yao, Chengyu Dong, Zihan Wang, Jingbo Shang

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

Comments Accepted to ACL 2024 Findings

Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification

Shanshan Xu, T. Y. S. S Santosh, Oana Ichim, Barbara Plank, Matthias Grabmair

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

Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection

Qutub Syed, Michael Paulitsch, Korbinian Hagn, Neslihan Kose Cihangir, Kay-Ulrich Scholl, Fabian Oboril, Gereon Hinz, Alois Knoll

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

Comments Paper accepted at CVPR SAIAD Workshop

Improved context-sensitive transformer model for inland vessel trajectory prediction

Kathrin Donandt, Karim Böttger, Dirk Söffker

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

Journal ref Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain, pp. 5903-5908

Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor

Chuankai Xu, Dongming Zhao, Bo Wang, Hanwen Xing

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

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz

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

Journal ref International Conference on Machine Learning (ICML), 2024

Is machine learning good or bad for the natural sciences?

David W. Hogg, Soledad Villar

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

Comments A Position Paper accepted for publication in the 2024 International Conference on Machine Learning (ICML)

Towards robust prediction of material properties for nuclear reactor design under scarce data -- a study in creep rupture property

Yu Chen, Edoardo Patelli, Zhen Yang, Adolphus Lye

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

Comments 8 pages, submitted to REC 2024 (International Workshop on Reliable Engineering Computing)

AI-Assisted Detector Design for the EIC (AID(2)E)

M. Diefenthaler, C. Fanelli, L. O. Gerlach, W. Guan, T. Horn, A. Jentsch, M. Lin, K. Nagai, H. Nayak, C. Pecar, K. Suresh, A. Vossen, T. Wang, T. Wenaus

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

Comments 11 pages, 4 figures, AI4EIC 2023 proceeding

Continual Deep Reinforcement Learning for Decentralized Satellite Routing

Federico Lozano-Cuadra, Beatriz Soret, Israel Leyva-Mayorga, Petar Popovski

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

Comments 30 pages, 11 figures

Precision Mars Entry Navigation with Atmospheric Density Adaptation via Neural Networks

Felipe Giraldo-Grueso, Andrey A. Popov, Renato Zanetti

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

Comments Accepted version, Journal of Aerospace Information Systems

Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation

Ruixin Yang, Dheeraj Rajagopal, Shirley Anugrah Hayati, Bin Hu, Dongyeop Kang

专题命中 幻觉与事实性 ：RLHF(abstract)；分类 cs.CL

Comments Accepted at ICLR 2024 Workshop on Reliable and Responsible Foundation Models

ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement

Saurabh Bhausaheb Zinjad, Amrita Bhattacharjee, Amey Bhilegaonkar, Huan Liu

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

Comments Accepted to SIGIR 2024 (Demo)

Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks

Mikkel Jordahn, Pablo M. Olmos

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

Comments Proceedings of the 41 st International Conference on Machine Learning (ICML) 2024

Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling

Yida Mu, Peizhen Bai, Kalina Bontcheva, Xingyi Song

专题命中 幻觉与事实性 ：DPO(abstract)；分类 cs.CL

Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules

Paul Hofman, Yusuf Sale, Eyke Hüllermeier

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

BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction

Ubaid Azam, Imran Razzak, Shelly Vishwakarma, Hakim Hacid, Dell Zhang, Shoaib Jameel

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

Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations

David Nadeau, Mike Kroutikov, Karen McNeil, Simon Baribeau

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

Comments 14 pages, 8 figures, 18 tables

Segmentation Re-thinking Uncertainty Estimation Metrics for Semantic Segmentation

Qitian Ma, Shyam Nanda Rai, Carlo Masone, Tatiana Tommasi

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

Comments Premature Submission: accidentally submitted before it was ready

Exploring Probabilistic Models for Semi-supervised Learning

Jianfeng Wang

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

Comments PhD Thesis, University of Oxford

Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting

Busra Asan, Abdullah Akgül, Alper Unal, Melih Kandemir, Gozde Unal

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

Comments Accepted as a workshop paper at "ICLR 2024 Tackling Climate Change with Machine Learning"

Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis

Jing Lin, Yu Zhang, Edwin Khoo

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

Comments 6 pages, 3 figures, accepted for poster presentation at Tackling Climate Change with Machine Learning workshop at NeurIPS 2021

Journal ref NeurIPS 2021 Workshop on Tackling Climate Change with Machine Learning

A Theoretical and Practical Framework for Evaluating Uncertainty Calibration in Object Detection

Pedro Conde, Rui L. Lopes, Cristiano Premebida

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

Comments Pre-print

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, Bryan Hooi

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

Comments The paper is accepted by ICLR 2024. The code is publicly available at https://github.com/MiaoXiong2320/llm-uncertainty

Fast and Simple Explainability for Point Cloud Networks

Meir Yossef Levi, Guy Gilboa

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