AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2025-09-18 至 2025-09-18 共收录 3 篇信号源：cs.CL, cs.AI, cs.LG

1. 测试时计算 3 篇

2509.13990 2025-09-18 cs.CL cs.AI cs.LG 67%

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency

Colin Hong, Xu Guo, Anand Chaanan Singh, Esha Choukse, Dmitrii Ustiugov

机构 * NTU Singapore（新加坡国立大学）； KTH Royal Institute of Technology（皇家理工学院）； Microsoft（微软公司）

专题命中测试时计算：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by EMNLP 2025 (Oral), 9 pages

2410.10857 2025-09-18 cs.CL cs.AI 62%

Mirror-Consistency: Harnessing Inconsistency in Majority Voting

Siyuan Huang, Zhiyuan Ma, Jintao Du, Changhua Meng, Weiqiang Wang, Zhouhan Lin

机构 * Shanghai Jiaotong University（上海交通大学）； Tiansuan Lab, Ant Group Co., Ltd.（蚂蚁集团天算实验室）； SJTU Paris Elite Institute of Technology（上海交通大学巴黎精英理工学院）

专题命中测试时计算：reasoning(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024 Findings

2411.18216 2025-09-18 cs.SE cs.CR cs.LG 57%

Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs

Samuele Pasini, Jinhan Kim, Tommaso Aiello, Rocio Cabrera Lozoya, Antonino Sabetta, Paolo Tonella

机构 * Samuele Pasini Universit\`a della Svizzera italiana, Switzerland Jinhan Kim Universit\`a della Svizzera italiana, Switzerland Tommaso Aiello SAP Labs France, France Rocio Cabrera Lozoya SAP Labs France, France Antonino Sabetta SAP Labs France, France Paolo Tonella Universit\`a della Svizzera italiana, Switzerland

专题命中测试时计算：reasoning(abstract)；分类 cs.LG