Abstract Large Language Models (LLMs) have demonstrated remarkable performance across various downstream tasks, as evidenced by numerous studies. Since 2022, generative AI has shown significant potential in diverse application domains, including gaming, film and television, media, and finance. By 2023, the global AI-generated content (AIGC) industry had attracted over $26 billion in investment. As LLMs become increasingly prevalent, prompt engineering has emerged as a key research area to enhance user-AI interactions and improve LLM performance. The prompt, which serves as the input instruction for the LLM, is closely linked to the model’s responses. Prompt engineering refines the content and structure of prompts, thereby enhancing the performance of LLMs without changing the underlying model parameters. Despite significant advancements in prompt engineering, a comprehensive and systematic summary of existing techniques and their practical applications remains absent. To fill this gap, we investigate existing techniques and applications of prompt engineering. We conduct a thorough review and propose a novel taxonomy that provides a foundational framework for prompt construction. This taxonomy categorizes prompt engineering into four distinct aspects: profile and instruction, knowledge, reasoning and planning, and reliability. By providing a structured framework for understanding its various dimensions, we aim to facilitate the systematic design of prompts. Furthermore, we summarize existing prompt engineering techniques and explore the applications of LLMs across various domains, highlighting their interrelation with prompt engineering strategies. This survey underscores the progress of prompt engineering and its critical role in advancing AI applications, ultimately aiming to provide a systematic reference for future research and applications.

Large language models (LLMs) are prominent for their superior ability in language understanding and generation. However, a notorious problem for LLM inference is low computational utilization caused by the memory bottleneck, since it typically requires large memory capacity and high bandwidth to process neural weights. By integrating processing cores into memory, Processing-In-Memory (PIM) architecture excels at alleviating memory bottleneck; with the recent release of the first commodity near-bank PIM hardware (NBP), PIM becomes off-the-shelf and shows great potential for accelerating LLM inference practically. However, simply shoehorning LLM inference on NBP can not achieve satisfactory performance due to its inherent limitations: weak compute performance, frequent cache misses caused by the limited working memory capacity, and poor inter-PIM-core communication bandwidth. To address these limitations, we propose MI-LLM, an efficient system deploying LLM inference on NBP hardware. Its key idea is to build NBP-aware Lookup Tables (LUTs) and completely replace multiplications with lookups on LUTs, thereby mitigating the limitation of weak compute performance. 1) To reduce the model accuracy drop caused by the use of LUT, MI-LLM tailors a learning-based LUT construction method to maintain the model accuracy. 2) To cope with frequent cache misses caused by LUT sizes far exceeding PIM working memory capacity, MI-LLM introduces the design of PIM-aware linear kernel, with the optimization of intra-row and inter-row reordering enabled, to enhance LUT lookup locality. 3) MI-LLM further proposes a model partitioning scheme to minimize inter-PIM-core communication. Kernel-level benchmarks reveal that MI-LLM achieves a 9% throughput improvement and an 11% increase in energy efficiency over GPU implementations. Compared to FP8 quantization, MI-LLM incurs only a 0.24 times increase in perplexity, demonstrating minimal accuracy degradation. Moreover, in our end-to-end evaluation, MI-LLM requires 80% fewer ALU operation ticks per output token than the GPU baseline.

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized corpora. The deficiency can come from long-distance dependencies which are hard to capture by language models, and overfitting to co-occurrence patterns and distracting clues in the training text. To address these issues, the paper proposes a method to enhance knowledge learning during language model pretraining, by enhancing elusive but important clues in text discovered by the language model themselves. We found that larger language models pay more attention to non-obvious but important clues, which are often overlooked by smaller language models. Therefore, we can identify these clues by contrasting the attention weights of large and small language models. We use the identified clues as a guide to perform token-dropout data augmentation on the training text, and observed a significant boost in both small and large models' performance in fact memorization. This shows that the behavior contrast between more and less-performant language models contains important clues for knowledge learning, and it can be "amplified" for a straight-forward improvement in knowledge learning efficiency.

Mastering medical knowledge is crucial for medical-specific LLMs. However, despite the existence of medical benchmarks like MedQA, a unified framework that fully leverages existing knowledge bases to evaluate LLMs' mastery of medical knowledge is still lacking. We propose PretexEval, a novel framework that dynamically generates reliable and diverse test samples to evaluate LLMs for any given medical knowledge base. We notice that test samples produced directly from knowledge bases by templates or LLMs may introduce factual errors and also lack diversity. To address these issues, our framework employs predicate equivalence transformations to produce a series of variants for any given medical knowledge point. Finally, these produced predicate variants are converted into textual language, resulting in a series of reliable and diverse test samples. Here, we use our proposed framework to systematically investigate the mastery of medical factual knowledge of 12 well-known LLMs, based on two knowledge bases that are crucial for clinical diagnosis and treatment. The evaluation results illustrate that current LLMs still exhibit significant deficiencies in fully mastering medical knowledge, despite achieving considerable success on some famous public benchmarks. These new findings provide valuable insights for developing medical-specific LLMs, highlighting that current LLMs urgently need to strengthen their comprehensive and in-depth mastery of medical knowledge before being applied to real-world medical scenarios.

Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a multi-cognitive-level evaluation framework for assessing LLMs in the medical domain in this study. The framework integrates existing medical datasets and introduces tasks targeting three cognitive levels: preliminary knowledge grasp, comprehensive knowledge application, and scenario-based problem solving. Using this framework, we systematically evaluate state-of-the-art general and medical LLMs from six prominent families: Llama, Qwen, Gemma, Phi, GPT, and DeepSeek. Our findings reveal a significant performance decline as cognitive complexity increases across evaluated models, with model size playing a more critical role in performance at higher cognitive levels. Our study highlights the need to enhance LLMs' medical capabilities at higher cognitive levels and provides insights for developing LLMs suited to real-world medical applications.

Inconsistent hallucinations remain a major challenge for large language models (LLMs), undermining the accuracy and reliability of fact-based reasoning in real-world applications. Existing approaches often rely on task-specific training or adaptation, such as hand-crafted synthetic datasets for domain tasks or solutions mainly focused on numerical reasoning, thereby limiting generalizability to broader, unseen NLP tasks. Inspired by the structural rigor and logical consistency of programming languages, we observe that fact-based texts can be mapped to programming structures due to their inherent patterns. We further propose FACT, a novel Fact-driven Alternating Code-text Training framework that alternates between text-to-code and code-to-text prediction. FACT is the first task-agnostic paradigm that embeds code and natural language in a shared semantic space, thereby transferring the logical consistency of code to LLM outputs in NLP tasks. Experiments show that with only a small subset of Wiki-40B-en for training, FACT reduces inconsistent hallucinations by 2.7%–8.0% and improves overall performance by 2.5%–6.1% in three leading LLMs and four diverse datasets covering QA and summarization tasks. This framework offers a new perspective on addressing challenging hallucinations in LLMs, contributing to more reliable AI.

Large Language Models (LLMs) are expected to possess comprehensive medical knowledge to support real-world clinical applications. While domain-specific fine-tuning effectively injects medical knowledge into LLMs, it often causes catastrophic forgetting of previously acquired knowledge and instruction-following capabilities. In this paper, we investigate this issue and reveal a pattern of proximity-dependent forgetting: knowledge that is semantically or topically close to the injected content is more likely to be forgotten, while unrelated knowledge shows minimal degradation. Moreover, we observe that existing mitigation techniques fail to address this type of forgetting effectively. Motivated by this observation and inspired by human learning mechanisms, we proposeInternAL (\Internal Knowledge Augmentation Learning), a novel approach that leverages LLMs' own internal knowledge to mitigate forgetting. InternAL first probes internal knowledge closely related to the injection by prompting the model with questions derived from the injected knowledge. This knowledge is then used to augment the original injection dataset, guiding the model to retain related prior knowledge during training. Experimental results on multiple LLMs (LLaMA, Qwen) demonstrate that InternAL significantly mitigates proximity-related forgetting while maintaining strong knowledge injection performance. Our findings provide new insights into the nature of catastrophic forgetting in medical knowledge injection and highlight a promising direction for robust domain adaptation in LLMs. Code and datasets are available at https://github.com/THUMLP/InternAL.

Relational Database Management Systems (RDBMSs) are crucial infrastructures supporting a wide range of applications, making bug mitigation within these systems essential. This study presents the first comprehensive analysis of bugs in three popular open-source RDBMSs—MySQL, SQLite, and openGauss. We manually examined 777 bugs across four dimensions, i.e., bug root causes, bug symptoms, bug distribution across modules, and the correlations between the studied aspects. We also analyzed the bug-triggering SQL statements to uncover test cases that cannot be generated by existing tools. We have made 12 findings, which throw lights on the development, maintenance and testing of RDBMS systems. Particularly, our findings reveal that bugs related to SQL data types and complex features, such as database triggers, procedures and database parameter settings, present significant opportunities for enhancing RDBMS bug detection and mitigation. Leveraging these insights, we developed a tool, SQLT, which effectively identified eight RDBMS bugs (five type-related), all verified by developers, with four subsequently fixed.

To explain the prediction result of a Deep Neural Network (DNN) model based on a given sample, LIME [1] and its derivatives have been proposed to approximate the local behavior of the DNN model around the data point via linear surrogates. Though these algorithms interpret the DNN by finding the key features used for classification, the random interpolations used by LIME would perturb the explanation result and cause the instability and inconsistency between repetitions of LIME computations. To tackle this issue, we propose G-LIME that extends the vanilla LIME through high-dimensional Bayesian linear regression using the sparsity and informative global priors. Specifically, with a dataset representing the population of samples (e.g., the training set), G-LIME first pursues the global explanation of the DNN model using the whole dataset. Then, with a new data point, -LIME incorporates an modified estimator of ElasticNet-alike to refine the local explanation result through balancing the distance to the global explanation and the sparsity/feature selection in the explanation. Finally, G-LIME uses Least Angle Regression (LARS) and retrieves the solution path of a modified ElasticNet under varying -regularization, to screen and rank the importance of features [2] as the explanation result. Through extensive experiments on real world tasks, we show that the proposed method yields more stable, consistent, and accurate results compared to LIME.

Lightweight fine-tuning is widely used as an important technique for efficiently adapting pre-trained language models (PLM) to downstream tasks. Despite the reduction in trainable parameters, existing lightweight fine-tuning methods are found to be effective in low-resource settings but often fail in high-resource settings, leading to unreliable outcomes. This limitation can be attributed to inflexible strategies: they identify the parameters of the model to be trained before fine-tuning and remain unchanged without taking into account the inherent variance of generalization ability in model components (i.e., feed-forward, attention layers) and potential changes during the fine-tuning process. In this paper, we introduce a simple but effective calibration for lightweight fine-tuning PLMs based on the matrix’s stable rank according to both model components and the training process. We proposed both theoretical analyses and experimental verification for the proposed calibration strategy. Considering efficiency, we further propose time-aware and structure-aware strategies to determine the most crucial time to commence the fine-tuning procedure and selectively apply parameter matrices for lightweight fine-tuning, respectively. Extensive experiments demonstrate the superiority of our proposed fine-tuning approach (average improvement 3.1 for GLUE score compared to lightweight fine-tuning method).

Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we propose a simple modification to causal language modeling called conditional finetuning, which performs language modeling conditioned on a context. We show that a context can "explain away" certain corpus statistics and make the model avoid learning them. In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases. This selective learning effect leads to less forgetting and better stability-plasticity tradeoff in domain finetuning, potentially benefitting lifelong learning with language models.

Pretrained language models can encode a large amount of knowledge and utilize it for various reasoning tasks, yet they can still struggle to learn novel factual knowledge effectively from finetuning on limited textual demonstrations. In this work, we show that the reason for this deficiency is that language models are biased to learn word co-occurrence statistics instead of true factual associations. We identify the differences between two forms of knowledge representation in language models: knowledge in the form of co-occurrence statistics is encoded in the middle layers of the transformer model and does not generalize well to reasoning scenarios beyond simple question answering, while true factual associations are encoded in the lower layers and can be freely utilized in various reasoning tasks. Based on these observations, we propose two strategies to improve the learning of factual associations in language models. We show that training on text with implicit rather than explicit factual associations can force the model to learn factual associations instead of co-occurrence statistics, significantly improving the generalization of newly learned knowledge. We also propose a simple training method to actively forget the learned co-occurrence statistics, which unblocks and enhances the learning of factual associations when training on plain narrative text. On both synthetic and real-world corpora, the two proposed strategies improve the generalization of the knowledge learned during finetuning to reasoning scenarios such as indirect and multi-hop question answering.

Matrix sketching, aimed at approximating a matrix A ∈ R N×d consisting of vector streams of length N with a smaller sketching matrix B ∈ R ℓ×d , ℓ ≪ N , has garnered increasing attention in fields such as large-scale data analytics and machine learning. A well-known deterministic matrix sketching method is the FreqentDirections algorithm, which achieves the optimal [EQUATION] space bound and provides a covariance error guarantee of ε = || A ⊤ A - B ⊤ B || 2 /|| A || 2 F. The matrix sketching problem becomes particularly interesting in the context of sliding windows, where the goal is to approximate the matrix A W , formed by input vectors over the most recent N time units. However, despite recent efforts, whether achieving the optimal [EQUATION] space bound on sliding windows is possible has remained an open question. In this paper, we introduce the DS-FD algorithm, which achieves the optimal [EQUATION] space bound for matrix sketching over row-normalized, sequence-based sliding windows. We also present matching upper and lower space bounds for time-based and unnormalized sliding windows, demonstrating the generality and optimality of DS-FD across various sliding window models. This conclusively answers the open question regarding the optimal space bound for matrix sketching over sliding windows. We conduct extensive experiments with both synthetic and real-world datasets, validating our theoretical claims and thus confirming the correctness and effectiveness of our algorithm, both theoretically and empirically.

Training images with data transformations, e.g., crops, shifts, rotations and color distortions, have been suggested as contrastive examples to evaluate the robustness of deep neural networks against data noises [1]. In this work, we propose a practical framework ContRE (which is the meaning of “against” in French) that uses Contrastive examples for DNN Robustness Estimation. Specifically, ContRE follows the assumption in [2], [3] that robust DNN models with good generalization performance are capable of extracting a consistent set of features and making consistent predictions from the same image under varying data transformations. Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContREadopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the robustness of DNN models, which correlates to the models’ generalization performance. To show the effectiveness and efficiency of ContRE, extensive experiments have been done using various DNN models, e.g., ResNet, VGGNet, DenseNet, EfficientNet, etc., on three open source benchmark datasets, i.e., CIFAR-10, CIFAR-100, and ImageNet, with thorough ablation studies and applicability analyses. Our experiment results confirm that ❨1❩ behaviors of deep models on contrastive examples are strongly correlated to what on the testing set, and ❨2❩ the robustness that ContRE calculates is a robust measure of generalization performance complementing to the testing set in various settings. Codes is to be publicly available.

Deep learning on edge devices is becoming increasingly important, especially with the explosion of IoT devices. For example, the total number of devices connected to IoT reaches 29 billion in 2022. Convolutional neural networks (CNNs), as common deep learning representatives, are among the most popular neural networks in knowledge and data engineering. However, CNN employs a high degree of computing. In comparison to the training phase, the inference process is more frequently done on low-power computing equipments, such as edge devices. The limited computing resource and high computation pressure limit the effective use of CNN algorithms at the edge. Fortunately, a minimal filtering algorithm called Winograd can reduce convolution calculations by minimizing multiplication operations. We find that Winograd convolution can be accelerated further bydeep reusetechnique, which reuses the similar data and computation processes. In this paper, we propose a new inference method, called DREW, which combines deep reuse with Winograd for further accelerating CNNs. DREW handles three difficulties. First, it can detect the similarities from the complex minimal filtering patterns by clustering. Second, it reduces the online clustering cost in a reasonable range. Third, it provides an adjustable method in clustering granularity balancing the performance and accuracy. We perform evaluation on Raspberry PI and NVIDIA Jetson AGX Xavier edge devices, and experiments show that on five popular networks, 1) DREW further accelerates the Winograd convolution by an average of 8.27× speedup. Even for the highly parallel Winograd implementation, DREW still can provide 2.21× speedup. 2) When DREW is applied to end-to-end Winograd CNN inferences, DREW achieves 5.94× the average performance speedup with no ($< $0.4%) accuracy loss. 3) Energy consumption is an important factor for inference in practice. DREW reduces the number of convolution operations to 10% of the original operations, thus achieving up to 60% energy-efficiency benefits than the original Winograd inference.

The tremendous computing capacity of GPU offers significant potential in processing hierarchically compressed text data without decompression. However, current GPU techniques offer only traversal-based text data analytics; random access is exceedingly inefficient, limiting their utility significantly. To address this issue, we develop a novel and widely applicable solution that prompts random access to hierarchically compressed text data without decompression in GPU memory. We address three main challenges for enabling efficient random access to compressed text data on GPUs. The first challenge is designing GPU data structures that facilitate random access. The second challenge is efficiently generating data structures on GPU. The CPU is inefficient when generating data structures for random access, and this inefficiency increases considerably when PCIe transmission is incorporated. The third challenge is query processing on compressed text data in GPU memory. Random accesses, such as data updates, cause massive conflicts among countless threads. In order to address the first challenge, we develop several compressed GPU data structures, including indexing within the intricate GPU memory hierarchy. To handle the second challenge, we propose a two-phase process for producing these data structures on GPU. For the third challenge, a double-parsing design is proposed as a solution to avoid conflicts. We evaluate our solution on three platforms, two server-grade GPU platforms and one edge-grade GPU platform, using five real-world datasets. Experimental results show that random access operations on GPU achieve an average speedup of 52.98× compared to the state-of-the-art solution.

GPU's powerful computational capacity holds great potentials for processing hierarchically-compressed data without decompression in data science domain. Unfortunately, existing GPU approaches offer only traversal-based data analytics; random access is extremely inefficient, substantially limiting their utility. To solve this problem, we develop a novel and broadly applicable optimization that enables efficient random access to hierarchically-compressed data without decompression in GPU memory. We address three major challenges for enabling efficient random access to compressed data on GPUs. The first challenge is designing GPU data structures that support random access. The second challenge is efficiently generating data structures on GPU. Generating data structures for random access is costly on the CPU, and the inefficiency increases dramatically when PCIe data transmission is incorporated. The third challenge is query processing on compressed data in GPU memory. Random accesses, including data updates, result in significant conflicts between massive threads. To solve the first challenge, we propose and modify a number of compressed data structures, including indexing within the complicated GPU memory hierarchy. To address the second challenge, we develop a two-phase process for generating these data structures on the GPU. To handle the third challenge, we propose a double-parsing design to avoid data conflicts. We evaluate our solution on two GPU platforms using five real-world datasets. Experiments show that the random access operations on GPU can achieve 65.04x average speedup compared to the state-of-the-art method.

There are plenty of parking spaces in big cities, but we often find nowhere to park. For example, New York has 1.4 million cars and 4.4 million on-street parking spaces, but it is still not easy to find a parking place near our destination, especially during peak hours. The reason is the lack of prediction of parking behavior. If we could provide parking behavior in advance, we can ease this parking problem that affects human well-being. We observe that parking lots have periodic parking patterns, which is an important factor for parking behavior prediction. Unfortunately, existing work ignores such periodic parking patterns in parking behavior prediction, and thus incurs low accuracy. To solve this problem, we propose PewLSTM, a novel periodic weather-aware LSTM model that successfully predicts the parking behavior based on historical records, weather, environments, weekdays, and events. PewLSTM includes a periodic weather-aware LSTM prediction module and an event prediction module, for predicting parking behaviors in regular days and events. PewLSTM is extremely useful for drivers and parking lot owners to improve customer experience. For example, the probability of parking space that will be available soon can be provided even if the parking lot is full. Based on 910,477 real parking records in 904 days from 13 parking lots, PewLSTM yields 93.84% parking prediction accuracy, which is about 30% higher than the state-of-the-art parking behavior prediction method. Additionally, we have analyzed parking behaviors in events like holidays and COVID-19. PewLSTM can handle parking behavior prediction in events and reaches 90.68 percent accuracy.

Time series data is widely used in scenarios such as supply chain, stock data analysis, and smart manufacturing. A number of time series database systems have been invented to manage and query large volumes of time series data. We observe that the existing benchmarks of time series databases are focused on workloads of complex analysis such as pattern matching and trend prediction whose performance may be highly affected by the data analysis algorithms, instead of the back-end databases. However, in many real applications of time series databases, people are more interested in the performance metrics such as data injection throughput and query processing time. A benchmark is still required to extensively compare the performance of time series databases in such metrics. We introduce such a benchmark called TS-Benchmark which majorly applies a scenario of device monitoring for wind turbines. A DCGAN-based data generation model is proposed to generate large volumes of time series data from some real time series data. The workloads are categorized into three folds: data loading (in batch), streaming data injection, and historical data access (for typical queries). We implement the benchmark and compare four representative time series databases: InfluxDB, TimescaleDB, Druid and OpenTSDB. The results are reported and analyzed.

Utilizing heterogeneous accelerators, especially GPUs, to accelerate machine learning tasks has shown to be a great success in recent years. GPUs bring huge performance improvements to machine learning and greatly promote the widespread adoption of machine learning. However, the discrete CPU-GPU architecture design with high PCIe transmission overhead decreases the GPU computing benefits in machine learning training tasks. To overcome such limitations, hardware vendors release CPU-GPU integrated architectures with shared unified memory. In this article, we design a benchmark suite for machine learning training on CPU-GPU integrated architectures, called iMLBench, covering a wide range of machine learning applications and kernels. We mainly explore two features on integrated architectures: 1) zero-copy, which means that the PCIe overhead has been eliminated for machine learning tasks and 2) co-running, which means that the CPU and the GPU co-run together to process a single machine learning task. Our experimental results on iMLBench show that the integrated architecture brings an average 7.1× performance improvement over the original implementations. Specifically, the zero-copy design brings 4.65× performance improvement, and co-running brings 1.78× improvement. Moreover, integrated architectures exhibit promising results from both performance-per-dollar and energy perspectives, achieving 6.50× performance-price ratio while 4.06× energy efficiency over discrete GPUs. The benchmark is open-sourced at https://github.com/ChenyangZhang-cs/iMLBench.

Compared to sequential learning models, graph-based neural networks exhibit some excellent properties, such as ability capturing global information. In this paper, we investigate graph-based neural networks for text classification problem. A new framework TensorGCN (tensor graph convolutional networks), is presented for this task. A text graph tensor is firstly constructed to describe semantic, syntactic, and sequential contextual information. Then, two kinds of propagation learning perform on the text graph tensor. The first is intra-graph propagation used for aggregating information from neighborhood nodes in a single graph. The second is inter-graph propagation used for harmonizing heterogeneous information between graphs. Extensive experiments are conducted on benchmark datasets, and the results illustrate the effectiveness of our proposed framework. Our proposed TensorGCN presents an effective way to harmonize and integrate heterogeneous information from different kinds of graphs.

External knowledge is often useful for natural language understanding tasks. We introduce a contextual text representation model called Conceptual-Contextual (CC) embeddings, which incorporates structured knowledge into text representations. Unlike entity embedding methods, our approach encodes a knowledge graph into a context model. CC embeddings can be easily reused for a wide range of tasks in a similar fashion to pre-trained language models. Our model effectively encodes the huge UMLS database by leveraging semantic generalizability. Experiments on electronic health records (EHRs) and medical text processing benchmarks showed our model gives a major boost to the performance of supervised medical NLP tasks.

Unsupervised word embeddings have become a popular approach of word representation in NLP tasks.However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance.We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings.A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way.As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without "forgetting."We apply the method to various NLP tasks and see a consistent improvement in performance.Evaluation also confirms the tuned word embeddings have better semantic properties.

Reading and understanding text is one important component in computer aided diagnosis in clinical medicine, also being a major research problem in the field of NLP. In this work, we introduce a question-answering task called MedQA to study answering questions in clinical medicine using knowledge in a large-scale document collection. The aim of MedQA is to answer real-world questions with large-scale reading comprehension. We propose our solution SeaReader---a modular end-to-end reading comprehension model based on LSTM networks and dual-path attention architecture. The novel dual-path attention models information flow from two perspectives and has the ability to simultaneously read individual documents and integrate information across multiple documents. In experiments our SeaReader achieved a large increase in accuracy on MedQA over competing models. Additionally, we develop a series of novel techniques to demonstrate the interpretation of the question answering process in SeaReader.

Similarity search is a primitive operation in various database applications. Thus far, a large number of access methods have been proposed to accelerate the similarity query processing. Nonetheless, these methods mostly focus on developing standalone systems by proposing new indices. Given the fact that existing RDBMS merely support traditional indices, it is of great necessity and practical importance to develop a standard RDBMS built-in index based approach to speeding up the query processing. In this demonstration, we introduce MSQL+, a plugin toolkit that enable users to answer similarity queries in metric spaces simply using standard SQL statements. This toolkit can help existing RDBMS to effectively and efficiently handle with big data due to the following three advantages. First, MSQL+ enables users to find similar objects by submitting SELECT-FROM-WHERE statements so that it can be easily integrated into existing RDBMS. Second, MSQL+ works in a more general data space. Objects of any type can be indexed by B + -trees and the query processing can be boosted by using index seeks, as long as the similarity function is metric. Third, MSQL+ supports the parallelization of both pre-processing and query processing in distributed RDBMS.

High-frequency trading (HFT) has always been welcomed because it benefits not only personal benefits but also the whole social welfare. While the recent advance of portfolio selection in HFT market enables to bring about more profit, it yields much contended OLTP workloads. Featuring exploiting the abundant parallelism, transaction pipeline, the state-of-the-art concurrency control (CC) mechanism, however, suffers from limited concurrency confronted with HFT workloads. Its variants that enable more parallel execution by leveraging fine-grained contention information also take little effect. To solve this problem, we for the first time observe and formulate the source of restricted concurrency as harmful ordering of transaction statements. To resolve harmful ordering, we propose PARE, a pipeline-aware reordered execution, to improve application performance by rearranging statements in order of their degrees of contention. In concrete, two mechanisms are devised to ensure the correctness of statement rearrangement and identify the degrees of contention of statements, respectively. We also study the off-line reordering problem. We prove that this problem is NP-hard and present an off-line reordering approach to approximate the optimal reordering strategy. Experiment results show that PARE can improve transaction throughput and reduce transaction latency on HFT applications by up to an order of magnitude than the state-of-the-art CC mechanism.

With the proliferation of graph-based applications, such as social network management and Web structure mining, update-intensive graph databases have become an important component of today’s data management platforms. Several techniques have been recently proposed to exploit locality on both data organization and computational model in graph databases. However, little investigation has been conducted on buffer management of graph databases. To the best of our knowledge, current buffer managers of graph databases suffer performance loss caused by unnecessary random I/O access. To solve this problem, we develop a novel batch replacement policy for buffer management. This policy enables us to maximally exploit sequential I/O to improve the performance of graph database. However, trivial solution produces impractical maintenance for replacement plan with maximal sequential I/O. To enable the policy, we first devise a segment tree-based buffer manager to efficiently maintain a optimal replacement plan. Unfortunately, segment tree-based solution becomes bottleneck in multi-core environment. To remedy this weakness, a B-tree-based buffer manager is further proposed. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of our method.

The proliferation of location-based social networks, such as Foursquare and Facebook Places, offers a variety of ways to record human mobility, including user generated geo-tagged contents, check-in services, and mobile apps. Although trajectory data is of great value to many applications, it is challenging to analyze and mine trajectory data due to the complex characteristics reflected in human mobility, which is affected by multiple contextual information. In this paper, we propose a Multi-Context Trajectory Embedding Model, called MC-TEM, to explore contexts in a systematic way. MC-TEM is developed in the distributed representation learning framework, and it is flexible to characterize various kinds of useful contexts for different applications. To the best of our knowledge, it is the first time that the distributed representation learning methods apply to trajectory data. We formally incorporate multiple context information of trajectory data into the proposed model, including user-level, trajectory-level, location-level, and temporal contexts. All the context information is represented in the same embedding space. We apply MC-TEM to two challenging tasks, namely location recommendation and social link prediction. We conduct extensive experiments on three real-world datasets. Extensive experiment results have demonstrated the superiority of our MC-TEM model over several state-of-the-art methods.

It is insufficient to search temporal text by only focusing on either time attribute or keywords today as we pay close attention to the evolution of event with time. Both temporal and textual constraints need to be considered in one single query, called Top-k Interval Keyword Query (TIKQ).In this paper, we presents a cloud-based system named INK that supports efficient execution of TIKQs with appropriate effectiveness on Hadoop and HBase. In INK, an Adaptive Index Selector (AIS) is devised to choose the better execution plan for various TIKQs adaptively based on the proposed cost model, and leverage two novel hybrid index modules (TriI and IS-Tree) to combine keyword and interval filtration seamlessly.

SUMMARY As the recent proliferation of social networks, mobile applications, and online services increased the rate of data gathering, to find near‐duplicate records efficiently has become a challenging issue. Related works on this problem mainly aim to propose efficient approaches on a single machine. However, when processing large‐scale dataset, the performance to identify duplicates is still far from satisfactory. In this paper, we try to handle the problem of duplicate detection applying MapReduce. We argue that the performance of utilizing MapReduce to detect duplicates mainly depends on the number of candidate record pairs and intermediate result size, which is related to the shuffle cost among different nodes in cluster. In this paper, we proposed a new signature scheme with new pruning strategies to minimize the number of candidate pairs and intermediate result size. The proposed solution is an exact one, which assures none duplicate record pair can be lost. The experimental results over both real and synthetic datasets demonstrate that our proposed signature‐based method is efficient and scalable. Copyright © 2012 John Wiley & Sons, Ltd.

SUMMARY With the rapid developments in video processing technologies, video data have increased rapidly and become popular in our daily life for both professional and consumer applications such as surveillance, education and entertainment. Because of the increasing processing workload, more and more queries with expensive video predicates are being implemented in a parallel environment for better performance. Such requirements entail that the data management system not only be able to store and access video content, but also be able to optimize queries that have expensive video predicates in an effective and efficient way in a cloud environment. In previous research literatures, parallel and distributed policies and query optimizations in relational database management systems are often based on the disk input/output (I/O) cost of involved operations and network transmission cost. However, for a query that contains expensive video predicates in a cloud environment, the traditional cost estimation model does not work well. Although researchers have proposed some approaches that can solve the problem in certain situations, there are still some unresolved issues, and these approaches need further optimizations. This paper is motivated by a real‐world large supermarket business data and video surveillance data management scenario in a parallel environment. By considering the characteristics of video data and their expensive processing, we present methods named operating results buffer and operating results buffer‐C for implementing expensive video predicates at simple node, mapping video data and executing expensive video predicates in a cloud environment, which reduce the cost of video data transmission and the invoking times of expensive video predicates. We propose a novel query optimization approach that reconstructs the join order‐based estimation for attribute cardinality and computes the total cost with I/O, network and expensive processing. This approach reduces the invoking times of expensive video predicates to a greater degree and gives a better solution for mixed query optimization, which contains traditional data types and large object operations in a cloud environment. Our query performance improves by 30% to 80% compared with existing expensive predicates query optimization methods. Copyright © 2011 John Wiley & Sons, Ltd.

Video has become popular in our daily life for both professional and consumer applications. Both low level video processing and high level semantic video analysis are critically computational tasks in application domains. Most of current video computing tools are developed for specific analytic tasks, they are lack higher level interoperability with database and treat database merely as a relational data storage engine rather than an analytic platform, which causes inefficient data access and massive amount of data movement. In this paper, we study how to support video data management over relational database, and present our initial solutions of video data storage mechanism, video data access method and efficient video analytics. We also illustrate our ongoing prototype system HybVideo that developed in a novel architecture. It integrates above solutions to tackle the major challenges of providing a platform for both storage and analysis of video data.

This paper presents a reference framework, called BUD, to manage a large shared bank of unstructured data. This paper lists several important issues on managing or maintaining the unstructured data in BUD. BUD stores and manages the ever-growing unstructured data by introducing a novel technique called free-table, which is a conceptual view for end-users and a physical entity maintained by transactional storage manager of BUD. Free-table is cell-oriented but not column-oriented as relational table. It can store various types of unstructured data in cell with different versions. Additionally, we study two cases, VMP and PXRDB, to show that our proposal is feasible and tractable.

It is widely realized that the integration of database and information retrieval techniques will provide users with a wide range of high quality services. In this paper, we study processing an l-keyword query, p1, p2, ···, pl, against a relational database which can be modeled as a weighted graph, G(V, E). Here V is a set of nodes (tuples) and E is a set of edges representing foreign key references between tuples. Let Vi V be a set of nodes that contain the keyword pi. We study finding top-k minimum cost connected trees that contain at least one node in every subset Vi, and denote our problem as GST-k. When k = 1, it is known as a minimum cost group Steiner tree problem which is NP-Complete. We observe that the number of keywords, l, is small, and propose a novel parameterized solution, with l as a parameter, to find the optimal GST-1, in time complexity O(3ln + 2l((l + log n)n + m)), where n and m are the numbers of nodes and edges in graph G. Our solution can handle graphs with a large number of nodes. Our GST-1 solution can be easily extended to support GST-k, which outperforms the existing GST-k solutions over both weighted undirected/directed graphs. We conducted extensive experimental studies, and report our finding.