嵌入模型是语义搜索、个性化推荐以及面向大语言模型的检索增强生成等人工智能应用的核心组成部分,因此需要高质量的训练数据。然而,人工数据整理的可扩展性有限,促使人们需要自动化方法来保证数据完整性。传统的无监督三元组挖掘能够自动生成训练数据,对嵌入模型训练至关重要,但会在无意中引入偏差和噪声,从而降低模型性能。针对这一问题,我们提出了GISTEmbed,这是一种通过引导模型在对比训练期间增强批内负样本选择的新策略。该方法不再依赖随机采样和批内负样本效用相等的假设,显著减少了由数据质量问题引起的噪声,并改善了模型微调效果。在Massive Text Embedding Benchmark(MTEB)上进行的基准测试表明,GISTEmbed在不同模型规模上均展现出持续的性能提升,并在部分类别中取得了最先进的结果。该框架通过利用功能强大但资源密集的大型模型的能力,使较小模型能够获得显著增强。GISTEmbed有望彻底改变高效小型模型的创建方式,使先进人工智能技术的获取更加民主化。让这些技术更加易用且具有成本效益,尤其是对于资源受限的应用而言,将显著扩大最先进人工智能解决方案在各行各业的影响力和可及性。
英文摘要:
Embedding models are integral to AI applications like semantic search, personalized recommendations, and retrieval augmented generation for LLMs, necessitating high-quality training data. However, the limited scalability of manual data curation prompts the need for automated methods to ensure data integrity. Traditional unsupervised triplet mining automates training data generation, crucial for embedding model training, yet inadvertently injects biases and noise, thereby degrading model performance. Addressing this, we introduce GISTEmbed, a novel strategy that enhances in-batch negative selection during contrastive training through a guide model. This approach departs from reliance on random sampling and equal utility assumption of batch negatives, significantly reducing noise from data quality issues and improving model fine-tuning. Benchmarked against the Massive Text Embedding Benchmark (MTEB), GISTEmbed showcases consistent performance improvements across various model sizes and achieves state-of-the-art results in select categories. This framework enables significant enhancements for smaller models by leveraging the capabilities of powerful yet resource-intensive large models. GISTEmbed can potentially revolutionize the creation of highly efficient, smaller models, democratizing access to advanced AI technologies. Making these technologies more accessible and cost-effective, especially for applications constrained by resources, significantly expands the impact and accessibility of state-of-the-art AI solutions across diverse sectors.
TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
Department of Computer and Information Science, University of Pennsylvania(计算机与信息科学系,宾夕法尼亚大学);School of Mathematics, Georgia Institute of Technology(数学学院,佐治亚理工学院);Department of Bioengineering, University of Pennsylvania(生物工程系,宾夕法尼亚大学)
Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection
School of Intelligence Science and Technology, Peking University(智能科学与技术学院,北京大学);State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室)
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
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空间安全学院);Baidu Inc(百度公司)
GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search
University of Macau(澳门大学);Renmin University of China(中国人民大学);Fudan University(复旦大学);Tsinghua University(清华大学);Zhejiang University(浙江大学);University of Liverpool(利物浦大学);Peking University(北京大学);Northeast Normal University(东北师范大学);Minzu University of China(民族大学)
Alignment-Aware Model Adaptation via Feedback-Guided Optimization
Department of Computer Science, University of British Columbia, Location, Canada(不列颠哥伦比亚大学计算机科学系);Vector Institute of AI, Toronto, Canada(人工智能向量研究所);Stony Brook University, New York, USA(石溪大学)
L2T-Tune:LLM-Guided Hybrid Database Tuning with LHS and TD3
University of Chinese Academy of Sciences(中国科学院大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Hangzhou Institute for Advanced Study, UCAS(杭州高等研究院)
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.(计算机科学与工程系,南方科技大学,深圳,中国);Department of Mathematics, Southern University of Science and Technology, Shenzhen, China.(数学系,南方科技大学,深圳,中国)
Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
Northwestern Polytechnical University(西北工业大学);Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究院(TeleAI),中国电信);Tsinghua University(清华大学);Hong Kong University of Science(香港科学大学);Shenzhen Research Institute of Northwestern Polytechnical University(西北工业大学深圳研究院)
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
Department of Computer Science(计算机科学系);Information Engineering, National Cheng Kung University(信息工程系,国立成功大学);Department of Artificial Intelligence, Chang Gung University(人工智能系,长庚大学);Department of Computer Science, National Tsing Hua University(计算机科学系,国立清华大学)
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
School of Computing and Information Technology, Great Bay University(计算与信息学院,大亚湾大学);Beijing Institute of Technology(北京理工大学);University of Warwick(沃里克大学);City University of Hong Kong (Dongguan)(香港城市大学(东莞));Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));College of Computer Science and Software Engineering, Shenzhen University(计算机科学与软件工程学院,深圳大学)
Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design
Texas A&M University(德克萨斯A&M大学);EvolutionaryScale(进化尺度);Seoul National University(首尔国立大学);Princeton University(普林斯顿大学);Genentech(基因泰克);University of Texas Health Science Center at Houston(德克萨斯大学健康科学中心休斯顿分校)
Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models
School of Intelligence Science and Technology, Nanjing University, China(南京大学智能科学与技术学院);National Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室)
Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework
The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding
Department of Computer and Information Science, University of Pennsylvania(宾夕法尼亚大学计算机与信息科学系);Department of Bioengineering, University of Pennsylvania(宾夕法尼亚大学生物工程系);School of Mathematics, Georgia Institute of Technology(佐治亚理工学院数学学院)