Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using the $d'_{\rm type2}$ metric is established to isolate metacognitive ability. The Evolution Strategy for Metacognitive Alignment (ESMA) is proposed, demonstrating robust generalization across unseen datasets, languages, and newly acquired knowledge. Finally, parameter analysis reveals that these improvements are driven by a sparse set of parameters, offering new pathways for targeted metacognitive optimization.
Not All Documents Are What You Need for Extracting Instruction Tuning Data
Department of Computer Science, Beijing Institute of Technology, Beijing, China（北京理工大学计算机科学系）；Sensetime Research, Shenzhen, China（深睿时代研究）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）；University of Arizona, USA（亚利桑那大学）；Meta, USA（Meta）
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Five AI Ltd.（Five AI有限公司）；University of Michigan（密歇根大学）；Harvard University（哈佛大学）；University of Oxford（牛津大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Copenhagen（哥本哈根大学）
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
ShanghaiTech University（上海科技大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Meituan（美团）；Alibaba Group（阿里巴巴集团）；The Hong Kong University of Science and Technology（香港科技大学）
What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；Meituan Group（美团集团）
What Transfers Under Source Shift? Definitions, Examples, and Fine-Tuning for Climate Disclosure Classification
School of Computing and Information Technology, University of Wollongong（卧龙岗大学计算与信息技术学院）；School of Business, University of Wollongong（卧龙岗大学商学院）；Business School, University of Sydney（悉尼大学商学院）；Business School, Macquarie University（麦考瑞大学商学院）
Historical Test-time Prompt Tuning for Vision Foundation Models
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；University of Chinese Academy of Sciences（中国科学院大学）
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）
Dalhousie University（达尔豪斯大学）；Vector Institute for Artificial Intelligence（向量人工智能研究院）；TU Delft（代尔夫特理工大学）；Swarthmore College（斯沃斯莫尔学院）；University of Warwick（华威大学）
SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
Shanghai Qi Zhi Institute（上海启智研究院）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Xiongan AI Institute（雄安人工智能研究院）
MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models
Washington University in St. Louis（华盛顿大学圣路易斯分校）；The University of British Columbia（不列颠哥伦比亚大学）；Google Research（谷歌研究）；Virginia Tech（弗吉尼亚理工大学）；University of California, Davis（加州大学戴维斯分校）；Sony AI（索尼人工智能）；University of California, Berkeley（加州大学伯克利分校）
Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?
SKLCCSE, School of Computer Science and Engineering, Beihang University（SKLCCSE，计算机科学与工程学院，北航）；School of Software, Beihang University（软件学院，北航）；Zhongguancun Laboratory, Beijing（中关村实验室，北京）
