arXivDaily arXiv每日学术速递 周一至周五更新

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。

2025-08-19 至 2025-08-19 共收录 8 信号源:cs.CL, cs.AI, cs.LG

1. 其他推理 8 篇

2508.12604 2025-08-19 cs.LG cs.AI 86%

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression

Yuyang Xu, Yi Cheng, Haochao Ying, Zhuoyun Du, Renjun Hu, Xing Shi, Wei Lin, Jian Wu

专题命中 其他推理 :reasoning(title,abstract);chain-of-thought(abstract);CoT(abstract);分类 cs.AI、cs.LG

Comments Work in progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11800 2025-08-19 cs.LG cs.AI 81%

Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes

Michael Bereket, Jure Leskovec

专题命中 其他推理 :reasoning(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10265 2025-08-19 cs.AI cs.LO 79%

Why Cannot Large Language Models Ever Make True Correct Reasoning?

Jingde Cheng

专题命中 其他推理 :reasoning(title,abstract);分类 cs.AI

Comments 8 pages. arXiv admin note: substantial text overlap with arXiv:2412.12408

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17811 2025-08-19 cs.CL cs.AI cs.DB 62%

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

Wenqi Pei, Hailing Xu, Hengyuan Zhao, Shizheng Hou, Han Chen, Zining Zhang, Pingyi Luo, Bingsheng He

专题命中 其他推理 :reasoning(abstract);分类 cs.CL、cs.AI

Comments DL4C @ ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10824 2025-08-19 cs.LG cs.CL 62%

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures

Parsa Omidi, Xingshuai Huang, Axel Laborieux, Bahareh Nikpour, Tianyu Shi, Armaghan Eshaghi

机构 * Huawei Technologies Canada(华为加拿大技术有限公司) Huawei Technologies Switzerland(华为瑞士技术有限公司)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19595 2025-08-19 cs.LG 57%

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos

机构 * Meta GenAI(Meta 生成式人工智能) Meta FAIR

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

Comments Published as a conference paper at ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11823 2025-08-19 cs.CL 57%

Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText

Krishna Chaitanya Marturi, Heba H. Elwazzan

机构 * Georgia Institute of Technology(佐治亚理工学院)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

Comments Text Simplification, hallucination detection, LLMs, CLEF 2025, SimpleText, CEUR-WS

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12728 2025-08-19 eess.SP 50%

LLM-RIMSA: Large Language Models driven Reconfigurable Intelligent Metasurface Antenna Systems

Yunsong Huang, Hui-Ming Wang, Qingli Yan, Zhaowei Wang

专题命中 其他推理 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏