指令微调（Instruction Tuning，IT）对让大语言模型（large language models，LLMs）适配以人为本的交互至关重要。近期研究进展表明，精心挑选一小部分高质量指令微调数据能显著提升大语言模型的性能。尽管如此，常见方法往往依赖额外模型或数据，这增加了成本，限制了广泛应用。在本研究中，我们提出了一种名为SelectIT的新方法，该方法利用大语言模型自身的基础能力。具体而言，我们利用大语言模型中存在的内在不确定性，更有效地筛选高质量指令微调数据，无需额外资源。此外，我们构建了一个经过筛选的指令微调数据集Selective Alpaca，它是将SelectIT应用于Alpaca-GPT4数据集得到的。实验结果表明，使用Selective Alpaca进行指令微调能大幅提升模型能力。SelectIT的鲁棒性也在多种基础模型和特定领域任务中得到了验证。我们的研究结果表明，更长、计算量更大的指令微调数据可能是更优质的指令微调数据来源，这为该领域的未来研究提供了宝贵见解。数据、代码和脚本可在https://github.com/Blue-Raincoat/SelectIT免费获取。
英文摘要：
Instruction tuning (IT) is crucial to tailoring large language models (LLMs) towards human-centric interactions. Recent advancements have shown that the careful selection of a small, high-quality subset of IT data can significantly enhance the performance of LLMs. Despite this, common approaches often rely on additional models or data, which increases costs and limits widespread adoption. In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself. Specifically, we exploit the intrinsic uncertainty present in LLMs to more effectively select high-quality IT data, without the need for extra resources. Furthermore, we introduce a curated IT dataset, the Selective Alpaca, created by applying SelectIT to the Alpaca-GPT4 dataset. Empirical results demonstrate that IT using Selective Alpaca leads to substantial model ability enhancement. The robustness of SelectIT has also been corroborated in various foundation models and domain-specific tasks. Our findings suggest that longer and more computationally intensive IT data may serve as superior sources of IT, offering valuable insights for future research in this area. Data, code, and scripts are freely available at https://github.com/Blue-Raincoat/SelectIT.
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
University of Melbourne, Melbourne, Australia；Brain Science Institute, Korea Institute of Science；Department of Computer Science；Engineering, Korea University, Seoul, Republic of Korea；Division of Bio-Medical Science \& Technology, University of Science；Technology KIST School, Seoul, Republic of Korea
No More, No Less: Task Alignment in Terminal Agents
CISPA Helmholtz Center for Information Security（CISPA 涅槃中心信息安全研究所）；ELLIS Institute Tübingen and MPI for Intelligent Systems（图宾根 ELLIS 研究所和智能系统 MPI）；Tübingen AI Center（图宾根人工智能中心）
Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization
Department of Computer Science and Engineering, The Ohio State University, USA（计算机科学与工程系，俄亥俄州立大学）；Translational Data Analytics Institute, The Ohio State University, USA（转化数据分析研究所，俄亥俄州立大学）；Department of Biomedical Informatics, The Ohio State University, USA（生物医学信息学系，俄亥俄州立大学）；College of Pharmacy, The Ohio State University, USA（药学院，俄亥俄州立大学）
MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（教育部下一代智能搜索与推荐工程技术研究中心）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）
CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing
Huawei Hong Kong AI Framework & Data Technologies Lab（华为香港AI框架与数据技术实验室）；The Hong Kong University of Science and Technology（香港科技大学）；Shanghai University of Finance and Economics（上海财经大学）
Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
Department of Computer Science, National University of Singapore, Singapore（新加坡国立大学计算机科学系）；Smart Systems Institute, National University of Singapore, Singapore, Singapore（新加坡国立大学智能系统研究所）
Role-aware Heuristic Episodic Attention for Conversational LLMs
National Key Laboratory of Parallel and Distributed Computing（平行与分布式计算国家重点实验室）；College of Computer Science and Technology（计算机科学与技术学院）；National University of Defense Technology（国防科学技术大学）
Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
Institute of Cyberspace Security, Zhejiang University of Technology（浙江工业大学网络空间安全研究院）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）；College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院）
Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Software, Nanjing University of Information Science and Technology (NUIST)（南京信息工程大学软件学院）；Department of Orthopedic, Bahawal Victoria Hospital（巴哈瓦尔维多利亚医院骨科部门）
MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation
School of Computer Science and Technology, Tianjin University, Tianjin, China（天津大学计算机科学与技术学院）；School of Software, Tsinghua University, Beijing, China（清华大学软件学院）；School of Information Resource Management, Renmin University of China,Beijing, China（中国人民大学信息资源管理学院）；School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China（上海交通大学人工智能学院）；Baidu Inc., Beijing, China（百度公司）
