With the prevalence of Large Language Models (LLMs), recent studies have shifted paradigms and leveraged LLMs to tackle the challenging task of Text-to-SQL. Because of the complexity of real world databases, previous works adopt the retrieve-then-generate framework to retrieve relevant database schema and then to generate the SQL query. However, efficient embedding-based retriever suffers from lower retrieval accuracy, and more accurate LLM-based retriever is far more expensive to use, which hinders their applicability for broader applications. To overcome this issue, this paper proposes Gen-SQL, a novel generate-ground-regenerate framework, where we exploit prior knowledge from the LLM to enhance embedding-based retriever and reduce cost. Experiments on several datasets are conducted to demonstrate the effectiveness and scalability of our proposed method. We release our code and data at https://github.com/jieshi10/gensql.

Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases.Different databases implement their own SQL dialects, leading to variations in syntax.As a result, SQL queries designed for one database may not execute properly in another, creating a dialect gap.Existing Text-to-SQL research primarily focuses on specific database systems, limiting adaptability to different dialects.This paper proposes a novel adaptive framework called Dialect-SQL, which employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.Given a question, we guide Large Language Models (LLMs) to first generate ORM code, which is then parsed into SQL queries targeted for specific databases.However, there is a lack of high-quality Textto-Code datasets that enable LLMs to effectively generate ORM code.To address this issue, we propose a bootstrapping approach to synthesize ORM code, where verified ORM code is iteratively integrated into a demonstration pool that serves as in-context examples for ORM code generation.Our experiments demonstrate that Dialect-SQL significantly enhances dialect adaptability, outperforming traditional methods that generate SQL queries directly.

Abstract In a service system, operations engineers generally deploy numerous monitoring mechanisms in system components to detect anomalies caused by system faults and generate alerts, also known as alarms, that record the phenomenon of anomalies. Due to the topological relationships between system components, a system fault in a system component may affect other components and result in various local anomalies and generate multiple alerts across different components. Therefore, to facilitate troubleshooting, alerts of the same system fault are usually correlated into one group, called alert incident. However, although there are existing approaches that can automatically correlate alerts for operations engineers, analyzing alert incidents still rely on manual work. In this paper, we propose an approach, VOCE (Virtual On-Call Engineer). Using the emerging capabilities of a large language model, VOCE can automatically comprehend the anomaly information described by alerts and emulate the process of operations engineers analyzing an alert incident. Extensive experiments conducted on real alert incidents and two popular large language models demonstrate the effectiveness and efficiency of VOCE in automatically analyzing alert incidents.

System logs are critical for understanding the runtime behavior of information systems, yet their semi-structured nature poses challenges for effective utilization. Log parsing addresses this by transforming logs into structured representations, facilitating downstream tasks such as anomaly detection and failure analysis. Traditional approaches relying on statistical features or deep learning struggle with semantic understanding, efficiency, and adaptability to unseen data. Large language models (LLMs) offer new opportunities with their advanced semantic capabilities, yet current LLM-based log parsing methods are limited by sequential processing inefficiencies, suboptimal sampling strategies, and lack of robust template refinement mechanisms. To address these challenges, we propose EPAS (Efficient Parsing via Asynchronous Scheduling), a novel parser that utilizes asynchronous scheduling to optimize LLM- based log parsing. EPAS introduces three key innovations: a dynamic asynchronous mechanism to decouple LLM-based parsing from scheduling, maximizing efficiency; a controversy-based sampling mechanism to provide examples that help accurately parse challenging words; and an LLM-based validation task to semantically refine templates with minimal overhead. Experiments on benchmark datasets demonstrate that EPAS significantly outperforms state-of-the-art methods, achieving over a 360% improvement in parsing efficiency while maintaining high accuracy. In addition, EPAS achieves the best average performance across all four metrics, highlighting its effectiveness in both efficiency and accuracy.1

System logs have long been recognized as valuable data for analyzing and diagnosing system failures. One fundamental task of log processing is to convert unstructured logs into structured logs through log parsing. All previous log parsing approaches follow a general framework that first segments each log into a token sequence and then computes similarity between two sequences. However, all existing approaches share the common drawback: the flat segmentation with fixed delimiters fails to understand the structural information of logs, which causes low parsing accuracy. To address this problem, we propose a novel log parsing approach, AS-Parser. Our approach introduces a hierarchical log segmentation mechanism that can adaptively segment logs into a tree structure. It can automatically recognize the appropriate delimiters and capture the common structural information. Moreover, we propose three improvements that enhance both the effectiveness and efficiency of our approach. On the public benchmark, AS-Parser performs best on 14 out of 16 datasets, with an average parsing accuracy of 0.943, far exceeding existing approaches.

Alerts, which record details about system failures, are crucial data for monitoring a online service system. Due to the complex correlation between system components, a system failure usually triggers a large number of alerts, making the traditional manual handling of alerts insufficient. Thus, automatically summarizing alerts is a problem demanding prompt solution. This paper tackles this challenge through a novel approach based on supervised learning. The proposed approach, OAS (Online Alert Summarizing), first learns two types of information from alerts, semantic information and behavior information, respectively. Then, OAS adopts a specific deep learning model to aggregate semantic and behavior representations of alerts and thus determines the correlation between alerts. OAS is able to summarize the newly reported alert online. Extensive experiments, which are conducted on real alert datasets from two large commercial banks, demonstrate the efficiency and the effectiveness of OAS.