Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning tasks into two separated components: knowledge retrieval and knowledge-free reasoning, and analyze the relationship between cross-lingual transferability and these two components. With adapted commonsense reasoning datasets and constructed knowledge-free reasoning datasets, we show that the knowledge-free reasoning capability can be nearly perfectly transferred across various source-target language directions despite the secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer. Moreover, by analyzing the hidden states and feed-forward network neuron activation during the reasoning, we show that higher similarity of hidden representations and larger overlap of activated neurons could explain the better cross-lingual transferability of knowledge-free reasoning than knowledge retrieval. Thus, we hypothesize that knowledge-free reasoning shares similar neurons in different languages for reasoning, while knowledge is stored separately in different languages. Our code and data is available at: https://github.com/NJUNLP/Knowledge-Free-Reasoning.
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
Institute for Artificial Intelligence, Tsinghua University (THUAI)（清华大学人工智能研究院）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Department of Automation, Tsinghua University（清华大学自动化系）；TMLR Group, Hong Kong Baptist University（香港浸会大学TMLR组）
Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Department of Linguistics and Translation, City University of Hong Kong（香港城市大学语言学及翻译学系）
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Harbin Institute of Technology（哈尔滨工业大学）；Singapore Management University（新加坡管理学院）；Monash University（墨尔本大学）；Singapore University of Technology and Design（新加坡科技设计大学）；National University of Singapore（国立新加坡大学）
Crystal: Introspective Reasoners Reinforced with Self-Feedback
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；FAIR, Meta（Meta 基础人工智能研究院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
University of Notre Dame（圣母大学）；University of Maryland, College Park（马里兰大学帕克分校）；University of Cambridge（剑桥大学）；Huazhong University of Science and Technology（华中科技大学）；Lehigh University（里海大学）
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Technical University of Munich（慕尼黑技术大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Oxford（牛津大学）；CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全中心）
ASUS Intelligent Cloud Services (AICS)（ASUS智能云服务（AICS））；NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE)（国立科技大学人工智能研究中心（NTU AI-CoRE））；National University of Singapore（新加坡国立大学）
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder
DCST, BNRist（DCST、BNRist；KIRC、人工智能研究院、清华大学，中国）；KIRC, Institute for Artificial Intelligence, Tsinghua University, China（中文语言文学系、北京大学，中国）；Department of Chinese Language and Literature, Peking University, China
Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
National University of Singapore（新加坡国立大学）；Southern University of Science and Technology（南方科技大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；City University of Hong Kong（香港城市大学）
Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation
Korea University Sejong Campus（韩国大学世宗校区）；Cardiff Metropolitan University（卡迪夫 Metropolitan 大学）；Seoul National University（首尔国立大学）；Bugil Academy（Bugil 学院）；Gyeonggi Provincial Office of Education（京畿省教育厅）；Loughborough University（洛桑大学）；Korea National University of Education（韩国教育大学）；Korea University（韩国大学）；Korean Educational Development Institute（韩国教育发展院）；Sungshin Women’s University（顺天堂女子大学）；Seoul National University of Education（首尔国立教育大学）；Korea Institute for Curriculum and Evaluation（韩国课程评价院）；Indiana University Bloomington（印第安纳大学布卢明顿分校）
