Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
冲突感知融合:通过结构化认知先验缓解大语言模型中的逻辑惯性
Qiming Bao, Xiaoxuan Fu, Michael Witbrock
机构
*
Xtracta & Strong AI Lab, University of Auckland(Xtracta与强人工智能实验室,奥克兰大学)
;
School of Humanities, China University of Political Science and Law(人文学院,中国政法大学)
;
Strong AI Lab, University of Auckland(强人工智能实验室,奥克兰大学)
专题命中
后训练与偏好优化
:large language model(title,abstract);language model(title,abstract);SFT(abstract,abstract_cn);LLM(abstract_cn)
Distilled Reinforcement Learning for LLM Post-training
用于大语言模型训练后处理的蒸馏强化学习
Chen Wang, Zhaochun Li, Jionghao Bai, Yining Zhang, Hexuan Deng, Ge Lan, Yue Wang
机构
*
College of Elite Engineers, Nankai University(南开大学精英工程师学院)
;
Zhongguancun Academy(中关村学院)
;
Beijing Institute of Technology(北京理工大学)
;
Zhejiang University(浙江大学)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
Harbin Institute of Technology(哈尔滨工业大学)
;
College of Software, Nankai University(南开大学软件学院)
专题命中
后训练与偏好优化
:LLM(title,abstract);post-training(title,abstract);large language model(abstract);language model(abstract)
Comments36 pages, including appendices. Revised version with updated theoretical analysis, supplementary material, figures and improved table formatting
SciForma: Structure-Faithful Generation of Scientific Diagrams
SciForma:科学图表的结构忠实生成
Yuxuan Luo, Peng Zhang, Xinjie Zhang, Xun Guo, Zhouhui Lian, Yan Lu
机构
*
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机技术研究所)
;
State Key Lab of CAD & CG, Zhejiang University(浙江大学CAD&CG国家重点实验室)
;
Microsoft Research Asia(微软亚洲研究院)
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
对齐调整如何塑造大语言模型中谄媚及相关线索诱导偏差的表征?
Prakhar Gupta, Terry Jingchen Zhang, Florent Draye, Bernhard Schölkopf, Zhijing Jin
机构
*
University of Michigan(密歇根大学)
;
Jinesis Lab, University of Toronto & Vector Institute(多伦多大学Jinesis实验室和向量研究所)
;
Max-Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
;
ELLIS Institute Tübingen(图宾根ELLIS研究所)