Large Language Model (LLM)-based Task-Oriented Dialogue (TOD) systems show promising performance in helping users achieve specific goals in a zero-shot setting. However, existing systems engage with users in a reactive manner, relying on a basic single-query mechanism with the knowledge base and employing passive policy planning. The proactive TOD systems, which can provide potentially helpful information and plan cross-domain multi-task dialogue policies, have not been well studied. In addition, effective evaluation methods are also lacking. To address these issues, we propose ProTOD, a novel LLM-based proactive TOD framework designed to improve system proactivity and goal completion. First, we design an adaptive exploratory retrieval mechanism to dynamically navigate domain knowledge. Second, we introduce a two-stage passive-to-proactive policy planner that effectively organizes knowledge and actions relationship. Finally, we develop two distinct user simulators with different personalities to simulate real-world interactions and propose a new error measure called Human-targeted Policy Edit Rate (HPER) for evaluation. Experimental results show that ProTOD achieves state-of-the-art (SOTA) performance, improving goal completion rates by 10% while significantly enhancing the proactive engagement.

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors, conditional logic, and architectural constraints; implicit data dependencies in service-oriented architectures are difficult to infer and handle correctly.To bridge this gap, we propose a novel step-by-step code generation framework named UML2Dep by leveraging unambiguous formal specifications of complex requirements. First, we introduce an enhanced Unified Modeling Language (UML) sequence diagram tailored for service-oriented architectures. This diagram extends traditional visual syntax by integrating decision tables and API specifications, explicitly formalizing structural relationships and business logic flows in service interactions to rigorously eliminate linguistic ambiguity. Second, recognizing the critical role of data flow, we introduce a dedicated data dependency inference (DDI) task. DDI systematically constructs an explicit data dependency graph prior to actual code synthesis. To ensure reliability, we formalize DDI as a constrained mathematical reasoning task through novel prompting strategies, aligning with LLMs’ excellent mathematical strengths. Additional static parsing and dependency pruning further reduce context complexity and cognitive load associated with intricate specifications, thereby enhancing reasoning accuracy and efficiency.Experimental results on our in-house industrial datasets demonstrate the effectiveness of the proposed framework. Specifically, our framework achieves strong performance, with 89.97% recall, 95.06% precision, and 92.33% F1 score on the DDI task. Furthermore, the integration of UML2Dep into the code generation pipeline also improves practical deployment, increasing compilation pass rate by 8.83% and unit test pass rate by 11.66%.

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code generation task to achieve remarkable performance. One main challenge of pre-trained models for code generation is the semantic gap between developers’ natural language requirements and source code. To address the issue, prior studies typically adopt a retrieval-augmented framework for the task, where the similar code snippets collected by a retrieval process can be leveraged to help understand the requirements and provide guidance for the generation process. In a retrieval-augmented framework, similar data can be retrieved from the database using a retrieval algorithm, and original input data can be fused with retrieved data by different fusion strategies. However, there is a lack of systematic study on the application of this framework for code generation, including the impact of the final generated results and the specific usage of the framework. In this article, we choose three popular pre-trained code models, namely CodeGen, UniXcoder, and CodeT5, to assess the impact of the quality and utilization of retrieved code on the retrieval-augmented framework. Our analysis shows that the retrieval-augmented framework is beneficial for improving the performance of the existing pre-trained models. We also provide suggestions on the utilization of the retrieval-augmented code generation framework: BM25 and Sequential Integration Fusion are recommended due to their convenience and superior performance. Sketch Filling Fusion, which extracts a sketch of relevant code, could help the model improve its performance further. Additionally, we conduct experiments to investigate the influence of the retrieval-augmented framework on large language models for code generation, showing the effectiveness of the framework, and we discuss the tradeoff between performance improvement and computational costs in each phase within the framework.

The exponential increase of data has motivated advances of data storage technologies. As a promising storage media, deoxyribonucleic acid (DNA) storage provides a much higher data density and superior durability, compared with state-of-the-art media. In this article, we provide a tutorial on DNA storage and its role in molecular communications (MCs). First, we introduce the fundamentals of DNA-based MCs and storage (MCS), discussing the basic process of performing DNA storage in MCS. Furthermore, we provide tutorials on how conventional coding schemes that are used in wireless communications can be applied to DNA-based MCS, along with numerical results. Finally, promising research directions on DNA-based data storage in MCs are introduced and discussed in this article.

Software plays a crucial role in our daily lives, and therefore the quality and security of software systems have become increasingly important. However, vulnerabilities in software still pose a significant threat, as they can have serious consequences. Recent advances in automated program repair have sought to automatically detect and fix bugs using data-driven techniques. Sophisticated deep learning methods have been applied to this area and have achieved promising results. However, existing benchmarks for training and evaluating these techniques remain limited, as they tend to focus on a single programming language and have relatively small datasets. Moreover, many benchmarks tend to be outdated and lack diversity, focusing on a specific codebase. Worse still, the quality of bug explanations in existing datasets is low, as they typically use imprecise and uninformative commit messages as explanations. To address these issues, we propose an automated collecting framework REEF to collect REal-world vulnErabilities and Fixes from open-source repositories. We focus on vulnerabilities since they are exploitable and have serious consequences. We develop a multi-language crawler to collect vulnerabilities and their fixes, and design metrics to filter for high-quality vulnerability-fix pairs. Furthermore, we propose a neural language model-based approach to generate high-quality vulnerability explanations, which is key to producing informative fix messages. Through extensive experiments, we demonstrate that our approach can collect high-quality vulnerability-fix pairs and generate strong explanations. The dataset we collect contains 4,466 CVEs with 30,987 patches (including 236 CWE) across 7 programming languages with detailed related information, which is superior to existing benchmarks in scale, coverage, and quality. Evaluations by human experts further confirm that our framework produces high-quality vulnerability explanations.

It is well known that 40%-50% of hepatocellular carcinoma (HCC) do not show increased 18F-fluorodeoxyglucose (FDG) uptake. Recent research studies have demonstrated that 11C-acetate may be a complementary tracer to FDG in positron emission tomography (PET) imaging of HCC in the liver. Quantitative dynamic modeling is, therefore, conducted to evaluate the kinetic characteristics of this tracer in HCC and nontumor liver tissue. A three-compartment model consisting of four parameters with dual inputs is proposed and compared with that of five parameters. Twelve regions of dynamic datasets of the liver extracted from six patients are used to test the models. Estimation of the adequacy of these models is based on Akaike Information Criteria (AIC) and Schwarz Criteria (SC) by statistical study. The forward clearance K = K1 * k3/(k2 + k3) is estimated and defined as a new parameter called the local hepatic metabolic rate-constant of acetate (LHMRAct) using both the weighted nonlinear least squares (NLS) and the linear Patlak methods. Preliminary results show that the LHMRAct of the HCC is significantly higher than that of the nontumor liver tissue. These model parameters provide quantitative evidence and understanding on the kinetic basis of C-acetate for its potential role in the imaging of HCC using PET.

Functional imaging techniques such as positron emission tomography (PET) has the potential for early diagnosis of malignant tumors. However, 40-50% of hepatocellular carcinoma (HCC), a common malignancy worldwide, can hardly be detected by the widely used F-2-fluoro-2-deoxy-D-glucose (FDG) PET. C-acetate PET has recently been found effective for detecting HCC. To perform quantitative analysis to obtain the diagnosis information, regions of interest (ROls) are needed to be extracted. Manual placement of ROIs is subject to operator's skill and time-consuming. Furthermore, the small sizes of some ROIs make the task even more difficult. In this paper, we propose an approach to segment the dynamic C-acetate PET liver images automatically. The curves extracted from some segmented ROIs are then fitted to the presented C-acetate liver model. Finally, the parameter K, which has been validated as an indicator for detecting HCC, can be calculated.