CommentsThis paper is a Stage 1 Registered Report. The study protocol and analysis plan were peer reviewed and accepted at SANER 2026 with a Continuity Acceptance (CA) score for Stage 2
KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures
KDCM:通过显式推理结构减少大语言模型中的幻觉
Jinbo Hao, Kai Yang, Qingzhen Su, Yifan Li, Chao Jiang
机构
*
School of Computer Engineering, Jiangsu Ocean University(江苏海洋大学计算机工程学院)
;
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院)
专题命中
推理与问题求解
:large language model(abstract);language model(abstract);分类 cs.CL
机构
*
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(西安交通大学人机混合增强智能国家重点实验室、视觉信息与应用国家工程研究中心、人工智能与机器人研究所)
;
Nankai University(南开大学)
;
The Hong Kong University of Science and Technology(Guangzhou)(香港科技大学(广州))
;
School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件学院)
专题命中
推理与问题求解
:large language model(abstract);language model(abstract);分类 cs.CL
机构
*
X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China(X-LANCE实验室,计算机科学学院,上海交通大学,中国)
;
Shanghai Artificial Intelligence Laboratory, China(上海人工智能实验室,中国)
;
East China University of Technology, China(东华大学,中国)
;
University of Texas at Arlington, USA(德克萨斯大学阿灵顿分校,美国)
专题命中
推理与问题求解
:large language model(abstract);language model(abstract);分类 cs.CL
Investigating CoT Monitorability in Large Reasoning Models
探究大型推理模型中的CoT可监控性
Shu Yang, Junchao Wu, Xilin Gong, Xuansheng Wu, Derek Wong, Ninghao Liu, Di Wang
机构
*
Provable Responsible AI and Data Analytics (PRADA) Lab(可证明负责任的人工智能与数据分析师实验室)
;
King Abdullah University of Science and Technology(卡布斯大学)
;
University of Georgia(佐治亚大学)
;
University of Macau(澳门大学)
SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation
SyncThink: 一种无需训练的策略,用于将推理饱和与推理终止对齐
Gengyang Li, Wang Cai, Yifeng Gao, Yunfang Wu
机构
*
National Key Laboratory for Multimedia Information Processing, Peking University(北京大学多媒体信息处理国家级重点实验室)
;
School of Software and Microelectronics, Peking University(北京大学软件与微电子学院)
;
School of Computer Science, Peking University(北京大学计算机科学学院)