Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information
通过关键信息的分步注意力混合层蒸馏提升小模型的推理能力
Yao Chen, Jiawei Sheng, Wenyuan Zhang, Tingwen Liu
机构
*
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
;
School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
专题命中
推理与问题求解
:large language model(abstract);language model(abstract);分类 cs.CL
机构
*
College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院)
;
Huazhong University of Science and Technology(华中科技大学)
;
The University of Hong Kong(香港大学)
;
ByteDance Seed(字节跳动种子)
;
Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身人工智能研究院)
;
Shanghai Key Laboratory of Multimodal Embodied AI(上海多模态具身人工智能重点实验室)
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
多智能体推理与协作中的弱链接优化
Haoyu Bian, Chaoning Zhang, Jiaquan Zhang, Xingyao Li, Yuanfang Guo, Wei Dong, Yang Yang
机构
*
University of Electronic Science and Technology of China(电子科技大学)
;
Beihang University(北航)
;
Xi'an University of Architecture and Technology(西安建筑科技大学)
专题命中
推理与问题求解
:LLM(abstract);分类 cs.CL、cs.AI
AI总结
本文提出WORC框架,通过识别并强化性能瓶颈智能体,提升多智能体系统的稳定性和泛化能力。
Comments13 pages, 4 figures. Submitted to CAAI Transactions on Intelligence Technology
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
何时信任工具?用于工具集成数学推理的自适应工具信任校准
Ruotao Xu, Yixin Ji, Yu Luo, Jinpeng Li, Dong Li, Peifeng Li, Juntao Li, Min Zhang
机构
*
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院)
;
Department of Foundation Model, 2012 Labs, Huawei(华为基础模型部门)
;
Harbin Institute of Technology, Shenzhen (HITSZ)(哈尔滨工业大学深圳(HITSZ))
机构
*
The Chinese University of Hong Kong(香港中文大学)
;
Central South University(中南大学)
;
Huawei Technologies Co., Ltd(华为技术有限公司)
;
The Chinese University of Hong Kong, Shenzhen(香港中文大学深圳校区)
Large Language Models for Market Research: A Data-augmentation Approach
用于市场研究的大型语言模型:一种数据增强方法
Mengxin Wang, Dennis J. Zhang, Heng Zhang
机构
*
Naveen Jindal School of Management, The University of Texas at Dallas(内维恩·金达管理学院,德克萨斯大学达拉斯分校)
;
Olin School of Business, Washington University in St. Louis(奥林商学院,圣路易斯华盛顿大学)
;
W. P. Carey School of Business, Arizona State University(W.P.凯里商学院,亚利桑那州立大学)
专题命中
评测与基准
:LLM(summary_cn,abstract);large language model(title,abstract);language model(title,abstract);分类 cs.AI、cs.LG
A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG
面向增强基于LLM的量子代码生成的PennyLane数据集
Abdul Basit, Nouhaila Innan, Muhammad Haider Asif, Minghao Shao, Muhammad Kashif, Alberto Marchisio, Muhammad Shafique
机构
*
Center for Quantum and Topological Systems (CQTS)(量子与拓扑系统中心(CQTS))
;
NYUAD Research Institute(纽约大学阿布扎克研究院)
;
New York University Abu Dhabi(纽约大学阿布扎克分校)
专题命中
评测与基准
:LLM(title,title_cn);large language model(abstract);language model(abstract);分类 cs.AI