Ninghao Liu, Qiaoyu Tan, Yuening Li, Hongxia Yang, Jingren Zhou, Xia Hu
Networks have been widely used as the data structure for abstracting real-world systems as well as organizing the relations among entities. Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction. Existing network embedding models comprehensively integrate all information of each node, such as links and attributes, towards a single embedding vector to represent the node's general role in the network. However, a real-world entity could be multifaceted, where it connects to different neighborhoods due to different motives or self-characteristics that are not necessarily correlated. For example, in a movie recommender system, a user may love comedies or horror movies simultaneously, but it is not likely that these two types of movies are mutually close in the embedding space, nor the user embedding vector could be sufficiently close to them at the same time. In this paper, we propose a polysemous embedding approach for modeling multiple facets of nodes, as motivated by the phenomenon of word polysemy in language modeling. Each facet of a node is mapped as an embedding vector, while we also maintain association degree between each pair of node and facet. The proposed method is adaptive to various existing embedding models, without significantly complicating the optimization process. We also discuss how to engage embedding vectors of different facets for inference tasks including classification and link prediction. Experiments on real-world datasets help comprehensively evaluate the performance of the proposed method.
Zhuolun Xiang, Bolin Ding, Xi He, Jingren Zhou
Local differential privacy (LDP) enables private data sharing and analytics without the need for a trusted data collector. Error-optimal primitives (for, e.g., estimating means and item frequencies) under LDP have been well studied. For analytical tasks such as range queries, however, the best known error bound is dependent on the domain size of private data, which is potentially prohibitive. This deficiency is inherent as LDP protects the same level of indistinguishability between any pair of private data values for each data downer. In this paper, we utilize an extension of $ε$-LDP called Metric-LDP or $E$-LDP, where a metric $E$ defines heterogeneous privacy guarantees for different pairs of private data values and thus provides a more flexible knob than $ε$ does to relax LDP and tune utility-privacy trade-offs. We show that, under such privacy relaxations, for analytical workloads such as linear counting, multi-dimensional range counting queries, and quantile queries, we can achieve significant gains in utility. In particular, for range queries under $E$-LDP where the metric $E$ is the $L^1$-distance function scaled by $ε$, we design mechanisms with errors independent on the domain sizes; instead, their errors depend on the metric $E$, which specifies in what granularity the private data is protected. We believe that the primitives we design for $E$-LDP will be useful in developing mechanisms for other analytical tasks, and encourage the adoption of LDP in practice.
Ziniu Wu, Amir Shaikhha, Rong Zhu, Kai Zeng, Yuxing Han, Jingren Zhou
Cardinality estimation (CardEst) is an essential component in query optimizers and a fundamental problem in DBMS. A desired CardEst method should attain good algorithm performance, be stable to varied data settings, and be friendly to system deployment. However, no existing CardEst method can fulfill the three criteria at the same time. Traditional methods often have significant algorithm drawbacks such as large estimation errors. Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment. In this paper, we revitalize the Bayesian networks (BN) for CardEst by incorporating the techniques of probabilistic programming languages. We present BayesCard, the first framework that inherits the advantages of BNs, i.e., high estimation accuracy and interpretability, while overcomes their drawbacks, i.e. low structure learning and inference efficiency. This makes BayesCard a perfect candidate for commercial DBMS deployment. Our experimental results on several single-table and multi-table benchmarks indicate BayesCard's superiority over existing state-of-the-art CardEst methods: BayesCard achieves comparable or better accuracy, 1-2 orders of magnitude faster inference time, 1-3 orders faster training time, 1-3 orders smaller model size, and 1-2 orders faster updates. Meanwhile, BayesCard keeps stable performance when varying data with different settings. We also deploy BayesCard into PostgreSQL. On the IMDB benchmark workload, it improves the end-to-end query time by 13.3%, which is very close to the optimal result of 14.2% using an oracle of true cardinality.
Wenqi Jiang, Zhenhao He, Shuai Zhang, Thomas B. Preußer, Kai Zeng, Liang Feng, Jiansong Zhang, Tongxuan Liu, Yong Li, Jingren Zhou, Ce Zhang, Gustavo Alonso
Deep neural networks are widely used in personalized recommendation systems. Unlike regular DNN inference workloads, recommendation inference is memory-bound due to the many random memory accesses needed to lookup the embedding tables. The inference is also heavily constrained in terms of latency because producing a recommendation for a user must be done in about tens of milliseconds. In this paper, we propose MicroRec, a high-performance inference engine for recommendation systems. MicroRec accelerates recommendation inference by (1) redesigning the data structures involved in the embeddings to reduce the number of lookups needed and (2) taking advantage of the availability of High-Bandwidth Memory (HBM) in FPGA accelerators to tackle the latency by enabling parallel lookups. We have implemented the resulting design on an FPGA board including the embedding lookup step as well as the complete inference process. Compared to the optimized CPU baseline (16 vCPU, AVX2-enabled), MicroRec achieves 13.8~14.7x speedup on embedding lookup alone and 2.5$~5.4x speedup for the entire recommendation inference in terms of throughput. As for latency, CPU-based engines needs milliseconds for inferring a recommendation while MicroRec only takes microseconds, a significant advantage in real-time recommendation systems.
Zhu Zhang, Chang Zhou, Jianxin Ma, Zhijie Lin, Jingren Zhou, Hongxia Yang, Zhou Zhao
Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient reasoning on long sequences with limited storage resources, memory augmented neural networks introduce a human-like write-read memory to compress and memorize the long input sequence in one pass, trying to answer subsequent queries only based on the memory. But they have two serious drawbacks: 1) they continually update the memory from current information and inevitably forget the early contents; 2) they do not distinguish what information is important and treat all contents equally. In this paper, we propose the Rehearsal Memory (RM) to enhance long-sequence memorization by self-supervised rehearsal with a history sampler. To alleviate the gradual forgetting of early information, we design self-supervised rehearsal training with recollection and familiarity tasks. Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information. We evaluate the performance of our rehearsal memory by the synthetic bAbI task and several downstream tasks, including text/video question answering and recommendation on long sequences.
Yang Li, Yu Shen, Wentao Zhang, Jiawei Jiang, Bolin Ding, Yaliang Li, Jingren Zhou, Zhi Yang, Wentao Wu, Ce Zhang, Bin Cui
End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning. Existing AutoML systems, however, suffer from scalability issues when applying to application domains with large, high-dimensional search spaces. We present VolcanoML, a scalable and extensible framework that facilitates systematic exploration of large AutoML search spaces. VolcanoML introduces and implements basic building blocks that decompose a large search space into smaller ones, and allows users to utilize these building blocks to compose an execution plan for the AutoML problem at hand. VolcanoML further supports a Volcano-style execution model - akin to the one supported by modern database systems - to execute the plan constructed. Our evaluation demonstrates that, not only does VolcanoML raise the level of expressiveness for search space decomposition in AutoML, it also leads to actual findings of decomposition strategies that are significantly more efficient than the ones employed by state-of-the-art AutoML systems such as auto-sklearn.
Yaliang Li, Daoyuan Chen, Bolin Ding, Kai Zeng, Jingren Zhou
Database indexes facilitate data retrieval and benefit broad applications in real-world systems. Recently, a new family of index, named learned index, is proposed to learn hidden yet useful data distribution and incorporate such information into the learning of indexes, which leads to promising performance improvements. However, the "learning" process of learned indexes is still under-explored. In this paper, we propose a formal machine learning based framework to quantify the index learning objective, and study two general and pluggable techniques to enhance the learning efficiency and learning effectiveness for learned indexes. With the guidance of the formal learning objective, we can efficiently learn index by incorporating the proposed sampling technique, and learn precise index with enhanced generalization ability brought by the proposed result-driven gap insertion technique. We conduct extensive experiments on real-world datasets and compare several indexing methods from the perspective of the index learning objective. The results show the ability of the proposed framework to help to design suitable indexes for different scenarios. Further, we demonstrate the effectiveness of the proposed sampling technique, which achieves up to 78x construction speedup while maintaining non-degraded indexing performance. Finally, we show the gap insertion technique can enhance both the static and dynamic indexing performances of existing learned index methods with up to 1.59x query speedup. We will release our codes and processed data for further study, which can enable more exploration of learned indexes from both the perspectives of machine learning and database.
Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring to Multi-Modality to Multi-Modality Multitask Mega-transformer, for unified pretraining on the data of single modality and multiple modalities. We scale the model size up to 10 billion and 100 billion parameters, and build the largest pretrained model in Chinese. We apply the model to a series of downstream applications, and demonstrate its outstanding performance in comparison with strong baselines. Furthermore, we specifically design a downstream task of text-guided image generation, and show that the finetuned M6 can create high-quality images with high resolution and abundant details.
Yuxing Han, Ziniu Wu, Peizhi Wu, Rong Zhu, Jingyi Yang, Liang Wei Tan, Kai Zeng, Gao Cong, Yanzhao Qin, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Jiangneng Li, Bin Cui
Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced CardEst methods (especially ML-based) have been proposed with outstanding estimation accuracy and inference latency. However, there exists no study that systematically evaluates the quality of these methods and answer the fundamental problem: to what extent can these methods improve the performance of query optimizer in real-world settings, which is the ultimate goal of a CardEst method. In this paper, we comprehensively and systematically compare the effectiveness of CardEst methods in a real DBMS. We establish a new benchmark for CardEst, which contains a new complex real-world dataset STATS and a diverse query workload STATS-CEB. We integrate multiple most representative CardEst methods into an open-source database system PostgreSQL, and comprehensively evaluate their true effectiveness in improving query plan quality, and other important aspects affecting their applicability, ranging from inference latency, model size, and training time, to update efficiency and accuracy. We obtain a number of key findings for the CardEst methods, under different data and query settings. Furthermore, we find that the widely used estimation accuracy metric(Q-Error) cannot distinguish the importance of different sub-plan queries during query optimization and thus cannot truly reflect the query plan quality generated by CardEst methods. Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods. We have made all of the benchmark data and evaluation code publicly available at https://github.com/Nathaniel-Han/End-to-End-CardEst-Benchmark.
Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang
In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https://github.com/OFA-Sys/OFA.
Chengqiang Lu, Jianwei Zhang, Yunfei Chu, Zhengyu Chen, Jingren Zhou, Fei Wu, Haiqing Chen, Hongxia Yang
In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia. However, the large model size and high run-time latency are serious impediments to applying them in practice, especially on mobile phones and Internet of Things (IoT) devices. To compress the model, considerable literature has grown up around the theme of knowledge distillation (KD) recently. Nevertheless, how KD works in transformer-based models is still unclear. We tease apart the components of KD and propose a unified KD framework. Through the framework, systematic and extensive experiments that spent over 23,000 GPU hours render a comprehensive analysis from the perspectives of knowledge types, matching strategies, width-depth trade-off, initialization, model size, etc. Our empirical results shed light on the distillation in the pre-train language model and with relative significant improvement over previous state-of-the-arts(SOTA). Finally, we provide a best-practice guideline for the KD in transformer-based models.
Qibin Chen, Junyang Lin, Yichang Zhang, Hongxia Yang, Jingren Zhou, Jie Tang
Quality product descriptions are critical for providing competitive customer experience in an e-commerce platform. An accurate and attractive description not only helps customers make an informed decision but also improves the likelihood of purchase. However, crafting a successful product description is tedious and highly time-consuming. Due to its importance, automating the product description generation has attracted considerable interests from both research and industrial communities. Existing methods mainly use templates or statistical methods, and their performance could be rather limited. In this paper, we explore a new way to generate the personalized product description by combining the power of neural networks and knowledge base. Specifically, we propose a KnOwledge Based pErsonalized (or KOBE) product description generation model in the context of e-commerce. In KOBE, we extend the encoder-decoder framework, the Transformer, to a sequence modeling formulation using self-attention. In order to make the description both informative and personalized, KOBE considers a variety of important factors during text generation, including product aspects, user categories, and knowledge base, etc. Experiments on real-world datasets demonstrate that the proposed method out-performs the baseline on various metrics. KOBE can achieve an improvement of 9.7% over state-of-the-arts in terms of BLEU. We also present several case studies as the anecdotal evidence to further prove the effectiveness of the proposed approach. The framework has been deployed in Taobao, the largest online e-commerce platform in China.
Yuting Ye, Xuwu Wang, Jiangchao Yao, Kunyang Jia, Jingren Zhou, Yanghua Xiao, Hongxia Yang
Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation. The two types of graphs can contain distinct and complementary information for the same entities/nodes. However, previous works focus either on knowledge graph embedding or behavior graph embedding while few works consider both in a unified way. Here we present BEM , a Bayesian framework that incorporates the information from knowledge graphs and behavior graphs. To be more specific, BEM takes as prior the pre-trained embeddings from the knowledge graph, and integrates them with the pre-trained embeddings from the behavior graphs via a Bayesian generative model. BEM is able to mutually refine the embeddings from both sides while preserving their own topological structures. To show the superiority of our method, we conduct a range of experiments on three benchmark datasets: node classification, link prediction, triplet classification on two small datasets related to Freebase, and item recommendation on a large-scale e-commerce dataset.
Rong Zhu, Wei Chen, Bolin Ding, Xingguang Chen, Andreas Pfadler, Ziniu Wu, Jingren Zhou
A recent line of works apply machine learning techniques to assist or rebuild cost-based query optimizers in DBMS. While exhibiting superiority in some benchmarks, their deficiencies, e.g., unstable performance, high training cost, and slow model updating, stem from the inherent hardness of predicting the cost or latency of execution plans using machine learning models. In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance. The key observation is that the relative order or rank of plans, rather than the exact cost or latency, is sufficient for query optimization. Lero employs a pairwise approach to train a classifier to compare any two plans and tell which one is better. Such a binary classification task is much easier than the regression task to predict the cost or latency, in terms of model efficiency and accuracy. Rather than building a learned optimizer from scratch, Lero is designed to leverage decades of wisdom of databases and improve the native query optimizer. With its non-intrusive design, Lero can be implemented on top of any existing DBMS with minimal integration efforts. We implement Lero and demonstrate its outstanding performance using PostgreSQL. In our experiments, Lero achieves near optimal performance on several benchmarks. It reduces the plan execution time of the native optimizer in PostgreSQL by up to 70% and other learned query optimizers by up to 37%. Meanwhile, Lero continuously learns and automatically adapts to query workloads and changes in data.
Chenliang Li, Hehong Chen, Ming Yan, Weizhou Shen, Haiyang Xu, Zhikai Wu, Zhicheng Zhang, Wenmeng Zhou, Yingda Chen, Chen Cheng, Hongzhu Shi, Ji Zhang, Fei Huang, Jingren Zhou
Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there is a growing trend to build agent framework that equips LLMs, such as ChatGPT, with tool-use abilities to connect with massive external APIs. In this work, we introduce ModelScope-Agent, a general and customizable agent framework for real-world applications, based on open-source LLMs as controllers. It provides a user-friendly system library, with customizable engine design to support model training on multiple open-source LLMs, while also enabling seamless integration with both model APIs and common APIs in a unified way. To equip the LLMs with tool-use abilities, a comprehensive framework has been proposed spanning over tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation for practical real-world applications. Finally, we showcase ModelScopeGPT, a real-world intelligent assistant of ModelScope Community based on the ModelScope-Agent framework, which is able to connect open-source LLMs with more than 1000 public AI models and localized community knowledge in ModelScope. The ModelScope-Agent library\footnote{https://github.com/modelscope/modelscope-agent} and online demo\footnote{https://modelscope.cn/studios/damo/ModelScopeGPT/summary} are now publicly available.
Weirui Kuang, Bingchen Qian, Zitao Li, Daoyuan Chen, Dawei Gao, Xuchen Pan, Yuexiang Xie, Yaliang Li, Bolin Ding, Jingren Zhou
LLMs have demonstrated great capabilities in various NLP tasks. Different entities can further improve the performance of those LLMs on their specific downstream tasks by fine-tuning LLMs. When several entities have similar interested tasks, but their data cannot be shared because of privacy concerns regulations, federated learning (FL) is a mainstream solution to leverage the data of different entities. However, fine-tuning LLMs in federated learning settings still lacks adequate support from existing FL frameworks because it has to deal with optimizing the consumption of significant communication and computational resources, data preparation for different tasks, and distinct information protection demands. This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution, which consists of the following components: (1) we build an end-to-end benchmarking pipeline, automizing the processes of dataset preprocessing, federated fine-tuning execution, and performance evaluation on federated LLM fine-tuning; (2) we provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios with low communication and computation costs, even without accessing the full model; (3) we adopt several accelerating and resource-efficient operators for fine-tuning LLMs with limited resources and the flexible pluggable sub-routines for interdisciplinary study. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings, which also yields valuable insights into federated fine-tuning LLMs for the research community. To facilitate further research and adoption, we release FS-LLM at https://github.com/alibaba/FederatedScope/tree/llm.
Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, Jingren Zhou
Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress in this field. Consequently, most existing works have only been able to support a limited range of interaction capabilities. In this paper, we develop the Qwen-Audio model and address this limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types, such as human speech, natural sounds, music, and songs, to facilitate universal audio understanding abilities. However, directly co-training all tasks and datasets can lead to interference issues, as the textual labels associated with different datasets exhibit considerable variations due to differences in task focus, language, granularity of annotation, and text structure. To overcome the one-to-many interference, we carefully design a multi-task training framework by conditioning on a sequence of hierarchical tags to the decoder for encouraging knowledge sharing and avoiding interference through shared and specified tags respectively. Remarkably, Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts. Building upon the capabilities of Qwen-Audio, we further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.
Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, Jingren Zhou
Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful SFT dataset, while their definitions remain obscure and lack quantitative analyses. In this work, we propose InsTag, an open-set fine-grained tagger, to tag samples within SFT datasets based on semantics and intentions and define instruction diversity and complexity regarding tags. We obtain 6.6K tags to describe comprehensive user queries. Then we analyze popular open-sourced SFT datasets and find that the model ability grows with more diverse and complex data. Based on this observation, we propose a data selector based on InsTag to select 6K diverse and complex samples from open-source datasets and fine-tune models on InsTag-selected data. The resulting models, TagLM, outperform open-source models based on considerably larger SFT data evaluated by MT-Bench, echoing the importance of query diversity and complexity. We open-source InsTag in https://github.com/OFA-Sys/InsTag.
Dawei Gao, Zitao Li, Xuchen Pan, Weirui Kuang, Zhijian Ma, Bingchen Qian, Fei Wei, Wenhao Zhang, Yuexiang Xie, Daoyuan Chen, Liuyi Yao, Hongyi Peng, Zeyu Zhang, Lin Zhu, Chen Cheng, Hongzhu Shi, Yaliang Li, Bolin Ding, Jingren Zhou
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms. At the same time, it is also armed with system-level support for managing and utilizing multi-modal data, tools, and external knowledge. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field.
Zhihao Fan, Jialong Tang, Wei Chen, Siyuan Wang, Zhongyu Wei, Jun Xi, Fei Huang, Jingren Zhou
Artificial intelligence has significantly advanced healthcare, particularly through large language models (LLMs) that excel in medical question answering benchmarks. However, their real-world clinical application remains limited due to the complexities of doctor-patient interactions. To address this, we introduce \textbf{AI Hospital}, a multi-agent framework simulating dynamic medical interactions between \emph{Doctor} as player and NPCs including \emph{Patient}, \emph{Examiner}, \emph{Chief Physician}. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and NPCs to evaluate LLMs' performance in symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance diagnostic accuracy through iterative discussions. Despite improvements, current LLMs exhibit significant performance gaps in multi-turn interactions compared to one-step approaches. Our findings highlight the need for further research to bridge these gaps and improve LLMs' clinical diagnostic capabilities. Our data, code, and experimental results are all open-sourced at \url{https://github.com/LibertFan/AI_Hospital}.