Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs
Integreat - Norwegian Centre for knowledge-driven machine learning（Integreat - 挪威知识驱动机器学习中心）；UiT - The Arctic University of Norway（UiT - 北极大学）；University of Oslo（奥斯陆大学）
Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya, Benjamin Ricaud
As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary verbosity. We introduce a trace-optional evaluation protocol that exactly decomposes token efficiency using three observables available even for closed models: completion rate, conditional correctness given completion, and generated length. When instance-level workload metadata is available, we further normalize generated length by declared task-implied work and separate mean verbalization overhead from workload-dependent scaling. When such metadata is absent, we define an auditable solver-derived workload scale and evaluate its stability under leave-self-out, leave-top-k, and held-out-reference-pool perturbations. We evaluate 14 shared open-weight models on CogniLoad, GSM8K, ProofWriter, and ZebraLogic. We further evaluate 11 additional models on CogniLoad, enabling a fine-grained analysis of reasoning-task difficulty factors: task length, intrinsic difficulty, and distractor density. Efficiency and overhead rankings remain stable across all benchmark pairs, more robustly than accuracy rankings, while the decomposition separates logic-limited, context-limited (truncation-driven), and verbosity-limited failure modes that look identical under accuracy-per-token. We release an evaluation artifact and reporting template, which elaborates on why an LLM is inefficient at reasoning.
How Likely Do LLMs with CoT Mimic Human Reasoning?
Zhejiang University（浙江大学）；School of Engineering, Westlake University（西湖大学工学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究院）
How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs
The University of Osaka（大阪大学）；UC Davis（加州大学戴维斯分校）；UC Berkeley（加州大学伯克利分校）；Peking University（北京大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Shanghai Jiao Tong University（上海交通大学）；NII（信息学研究所（日本））；City University of Hong Kong（香港城市大学）
Decomposing Refusal Steering in Mixture-of-Experts Models
Department of Interdisciplinary Studies（交叉学科研究部）；University of Montana（蒙大拿大学）；Department of Pharmacy Practice & Science（药学与科学系）；University of Arizona（亚利桑那大学）；European Bioinformatics Institute（欧洲生物信息研究所）；European Molecular Biology Laboratory（欧洲分子生物学实验室）；Wellcome Genome Campus（沃氏基因组校园）
Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
The Hong Kong University of Science and Technology（香港科学与技术大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Zhejiang University（浙江大学）；Peking University（北京大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Surrey（萨里大学）
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University（吉林大学符号计算与知识工程重点实验室）；RIKEN Center for Advanced Intelligence Project（RIKEN高级智能项目中心）；Graduate School of Frontier Sciences, University of Tokyo（东京大学前沿科学研究生院）
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Nankai University（南开大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Fudan University（复旦大学）；Johns Hopkins University（约翰霍普金斯大学）；Wuhan University（武汉大学）；University of Science and Technology of China（中国科学技术大学）
Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning
Yangzhou University（扬州大学）；Auburn University（亚伯拉罕大学）；University of South Dakota（南达科他大学）；Institute for Clarity in Documentation（文档清晰研究所）；Inria Paris-Rocquencourt（巴黎-罗quentourt研究所）；Rajiv Gandhi University（拉贾夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）
Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学关键实验室，计算机科学学院，复旦大学）；School of Data Science, Fudan University（数据科学学院，复旦大学）；Ant Group（蚂蚁集团）
Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization
Faculty of Applied Sciences, Macao Polytechnic University（澳门理工大学应用科学学院）；Computer Science and Communication Research Center, School of Technology and Management, Polytechnic of Leiria（莱里亚理工学院技术与管理学院计算机科学与通信研究中心）；Institute of International Language Services Studies, Macau Millennium College（澳门 millennium 学院国际语言服务研究学院）；CISUC, Department of Informatics Engineering, University of Coimbra（科英布拉大学信息工程系 CISUC）
