Hallucination as a Feature, not a Defect: Evaluating a multi-agent architecture to transform speculative language-model outputs into testable scientific hypotheses
幻觉作为特征而非缺陷:评估一种将推测性语言模型输出转化为可检验科学假说的多智能体架构
Nicolas Rodriguez-Alvarez (IES Parquesol, Valladolid, Spain)
Comments25 pages. Bilingual: full English version followed by the complete Spanish version. Includes an exploratory paired baseline and ablation study (6 conditions). Code and data: this https URL (https://doi.org/10.5281/zenodo.20649714)
LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages
Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training
基于协同蒸馏发现与双引导鲁棒训练的开放词汇三维目标检测
Shangbo Yuan, Jie Xu, Xiaofeng Zhu, Na Zhao
机构
*
School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院)
;
Singapore University of Technology and Design(新加坡科技设计大学)
;
School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院)