大模型对齐与安全

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian Lin, Yanlin Qi, Yizhang Zhu, Themis Palpanas, Chengliang Chai, Nan Tang, Yuyu Luo

机构 * HKUST (GZ)（香港科技大学（广州）） ； Université Paris Cité（巴黎Cité大学） ； BIT（北京理工大学） 纠错

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

A Survey on Data-Driven Modeling of Human Drivers' Lane-Changing Decisions

Linxuan Huang, Dong-Fan Xie, Li Li, Zhengbing He

机构 * School of Systems Science, Beijing Jiaotong University（北京交通大学系统科学学院） ； Department of Automation, BNRist, Tsinghua University（清华大学自动化系） ； Laboratory for Information and Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室） 纠错

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

Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future Directions

Adithya Kulkarni, Fatimah Alotaibi, Xinyue Zeng, Longfeng Wu, Tong Zeng, Barry Menglong Yao, Minqian Liu, Shuaicheng Zhang, Lifu Huang, Dawei Zhou

机构 * Virginia Tech（弗吉尼亚理工大学） ； University of California, Davis（加州大学戴维斯分校） 纠错

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

Uncertainty Quantification for Machine Learning in Healthcare: A Survey

L. Julián Lechuga López, Shaza Elsharief, Dhiyaa Al Jorf, Firas Darwish, Congbo Ma, Farah E. Shamout

机构 * New York University（纽约大学） ； New York University Abu Dhabi（纽约大学阿布扎赫尔分校） 纠错

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

Comments 46 pages, 3 figures, 2 tables, AHLI Conference on Health, Inference, and Learning (CHIL)

Multivariate Conformal Selection

Tian Bai, Yue Zhao, Xiang Yu, Archer Y. Yang

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

Comments 25 pages, 4 figures. Accepted to ICML 2025

Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models

Makoto Sato

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

Confidence Estimation for Error Detection in Text-to-SQL Systems

Oleg Somov, Elena Tutubalina

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

Comments 15 pages, 11 figures, to be published in AAAI 2025 Proceedings

Large Language Models as Quasi-crystals: Coherence Without Repetition in Generative Text

Jose Manuel Guevara-Vela

机构 * School of Engineering and Physical Sciences, Heriot-Watt University（工程与物理科学学院，赫瑞斯泰大学） 纠错

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

Comments The discussion was restructured to add limitations to the analogy and other clarifications

Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs

Gabriel Freedman, Francesca Toni

机构 * Department of Computing, Imperial College London, UK（计算系，帝国理工学院伦敦分校） 纠错

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

Comments 8 pages, 4 figures

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Zhiwei Yang, Yucong Meng, Kexue Fu, Feilong Tang, Shuo Wang, Zhijian Song

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

Comments CVPR2025

MedCT: A Clinical Terminology Graph for Generative AI Applications in Healthcare

Ye Chen, Dongdong Huang, Haoyun Xu, Cong Fu, Lin Sheng, Qingli Zhou, Yuqiang Shen, Kai Wang

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

Comments Accepted into ICCS 2025 and published in Springer's LNCS Series

REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models

DongGeon Lee, Hwanjo Yu

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

Comments Accepted to SemEval@ACL 2025

Bonsai: Interpretable Tree-Adaptive Grounded Reasoning

Kate Sanders, Benjamin Van Durme

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

Comments 9 pages, preprint

Persuasive Calibration

Yiding Feng, Wei Tang

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

Do LLMs estimate uncertainty well in instruction-following?

Juyeon Heo, Miao Xiong, Christina Heinze-Deml, Jaya Narain

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

DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection

Sangpil Youm, Brodie Mather, Chathuri Jayaweera, Juliana Prada, Bonnie Dorr

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

Comments 15 pages, 6 figures, Accepted to The 29th International Conference on Natural Language & Information Systems (NLDB 2024)

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts

Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra

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

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

Xinyue Fang, Zhen Huang, Zhiliang Tian, Minghui Fang, Ziyi Pan, Quntian Fang, Zhihua Wen, Hengyue Pan, Dongsheng Li

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

Comments Accepted by AAAI25

An Empirical Analysis of Uncertainty in Large Language Model Evaluations

Qiujie Xie, Qingqiu Li, Zhuohao Yu, Yuejie Zhang, Yue Zhang, Linyi Yang

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

Comments ICLR 2025

Zero-shot Load Forecasting for Integrated Energy Systems: A Large Language Model-based Framework with Multi-task Learning

Jiaheng Li, Donghe Li, Ye Yang, Huan Xi, Yu Xiao, Li Sun, Dou An, Qingyu Yang

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

When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges

Abdenour Hadid, Tanujit Chakraborty, Daniel Busby

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

Journal ref Expert Systems, 2024, Volume: 41, Issue: 10

Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs

Premtim Sahitaj, Iffat Maab, Junichi Yamagishi, Jawan Kolanowski, Sebastian Möller, Vera Schmitt

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

Probabilistic Artificial Intelligence

Andreas Krause, Jonas Hübotter

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

Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model

Hadas Ben-Atya, Naama Gavrielov, Zvi Badash, Gili Focht, Ruth Cytter-Kuint, Talar Hagopian, Dan Turner, Moti Freiman

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

ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports

Romain Hardy, Sung Eun Kim, Du Hyun Ro, Pranav Rajpurkar

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

Comments Accepted to AIMedHealth 10 pages, 5 figures

Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?

Ipek Baris Schlicht, Zhixue Zhao, Burcu Sayin, Lucie Flek, Paolo Rosso

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

Comments 9 pages. Short paper appeared at 47th European Conference on Information Retrieval (ECIR 2025)

Load and Renewable Energy Forecasting Using Deep Learning for Grid Stability

Kamal Sarkar

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

Journal ref Proceedings of How AI can help in Green Energy, 24 Dec 2024, Science City , Kolkata, India

A 65 nm Bayesian Neural Network Accelerator with 360 fJ/Sample In-Word GRNG for AI Uncertainty Estimation

Zephan M. Enciso, Boyang Cheng, Likai Pei, Jianbo Liu, Steven Davis, Michael Niemier, Ningyuan Cao

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

Comments 7 pages, 12 figures

A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation

Steven Landgraf, Rongjun Qin, Markus Ulrich

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

A Soft Sensor Method with Uncertainty-Awareness and Self-Explanation Based on Large Language Models Enhanced by Domain Knowledge Retrieval

Shuo Tong, Han Liu, Runyuan Guo, Wenqing Wang, Xueqiong Tian, Lingyun Wei, Lin Zhang, Huayong Wu, Ding Liu, Youmin Zhang

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