Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
承诺下的一致性:探究LLM逻辑推理中的泛化与空洞记忆
Noor Islam S. Mohammad, Mahmudul Hasan
机构
*
Department of Computer Science, Informatics Institute, Istanbul Technical University(伊斯坦布尔技术大学信息学研究所计算机科学系)
;
School of Information Technology, Deakin University(迪肯大学信息技术学院)
专题命中
推理与问题求解
:LLM(title,title_cn);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG
An Empirical Study of LLM-Generated Specifications for VeriFast
LLM 生成的 VeriFast 规范实证研究
Wen Fan, Minh Tran, Sanya Dod, Xin Hu, Marilyn Rego, Danning Xie, Jenna DiVincenzo, Lin Tan
机构
*
Purdue University(普渡大学)
;
University of Michigan(密歇根大学)
;
Meta
;
Ann Arbor, Michigan, USA(美国密歇根州安阿伯)
;
Menlo Park, California, USA(美国加州Menlo Park)
;
West Lafayette, Indiana, USA(美国印第安纳州西拉法叶)
专题命中
推理与问题求解
:LLM(title,title_cn);large language model(abstract);language model(abstract);prompting(abstract)
SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection
SICI:一种揭示LLM立场检测中相变的语义-语用复杂度指数
Fuqiang Niu, Bowen Zhang
机构
*
School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学网络空间安全学院)
;
School of Artificial Intelligence, Shenzhen Technology University(深圳技术大学人工智能学院)