arXiv subjects

Çağatay Demiralp

Publications and source records attributed to Çağatay Demiralp.

At least 19 recordsLinked to original sources

arXiv2026

BEAVER: An Enterprise Benchmark for Text-to-SQL

Existing text-to-SQL benchmarks have largely been constructed from public databases with well-structured schemas and simplistic question-SQL pairs. While large language models (LLMs) excel on these settings, their efficacy in complex private enterprise environments, characterized by intricate schemas, domain knowledge, and analytical user queries involving sophisticated structures and functions, remains unproven. To bridge this gap, we introduce BEAVER, the first text-to-SQL benchmark derived from private data warehouses. It comprises 9128 question-SQL pairs sourced from real-world query logs and 812 tables across 19 diverse domains. Building this benchmark is challenging because (1) enterprise query logs are scarce due to privacy constraints, and (2) existing all-or-nothing evaluation metrics based on accuracy make error diagnosis difficult -- especially when producing a correct query involves solving multiple compounded challenges, such as domain knowledge and query complexity. We address these issues at two levels. At the dataset level, we synthesize high-fidelity, expert-verified queries that increase dataset size and isolate individual challenges or combine them, producing queries focused on domain knowledge, query complexity, and both. At the evaluation level, we provide human annotations and evaluation metrics for five critical subtasks to enable fine-grained analysis. Our evaluation reveals a significant performance gap compared to existing benchmarks: SOTA agentic frameworks using the advanced model GPT-5.2 achieve only 10.8% accuracy. When provided with all subtask annotations as oracle hints, accuracy increases to 30.1%, confirming that a major bottleneck lies in correctly resolving these subtasks. Finally, we provide a taxonomy of the residual errors that persist even with subtask hints, identifying specific challenges such as the use of advanced functions.

cs.CL↗

arXiv2026

BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation

Large language models (LLMs) have been successfully applied to many tasks, including text-to-SQL generation. However, much of this work has focused on publicly available datasets, such as Fiben, Spider, and Bird. Our earlier work showed that LLMs are much less effective in querying large private enterprise data warehouses and released Beaver, the first private enterprise text-to-SQL benchmark. To create Beaver, we leveraged SQL logs, which are often readily available. However, manually annotating these logs to identify which natural language questions they answer is a daunting task. Asking database administrators, who are highly trained experts, to take on additional work to construct and validate corresponding natural language utterances is not only challenging but also quite costly. To address this challenge, we introduce BenchPress, a human-in-the-loop system designed to accelerate the creation of domain-specific text-to-SQL benchmarks. Given a SQL query, BenchPress uses retrieval-augmented generation (RAG) and LLMs to propose multiple natural language descriptions. Human experts then select, rank, or edit these drafts to ensure accuracy and domain alignment. We evaluated BenchPress on annotated enterprise SQL logs, demonstrating that LLM-assisted annotation drastically reduces the time and effort required to create high-quality benchmarks. Our results show that combining human verification with LLM-generated suggestions enhances annotation accuracy, benchmark reliability, and model evaluation robustness. By streamlining the creation of custom benchmarks, BenchPress offers researchers and practitioners a mechanism for assessing text-to-SQL models on a given domain-specific workload. BenchPress is freely available via our public GitHub repository at https://github.com/fabian-wenz/enterprise-txt2sql and is also accessible on our website at http://dsg-mcgraw.csail.mit.edu:5000.

cs.CL↗

arXiv2025

What-if Analysis for Business Professionals: Current Practices and Future Opportunities

What-if analysis (WIA) is essential for data-driven decision-making, allowing users to assess how changes in variables impact outcomes and explore alternative scenarios. Existing WIA research primarily supports the workflows of data scientists and analysts, and largely overlooks business professionals who engage in WIA through non-technical means. To bridge this gap, we conduct a two-part user study with 22 business professionals across marketing, sales, product, and operations roles. The first study examines their existing WIA practices, tools, and challenges. Findings reveal that business professionals perform many WIA techniques independently using rudimentary tools due to various constraints. We then implement representative WIA techniques in a visual analytics prototype and use it as a probe to conduct a follow-up study evaluating business professionals' practical use of the techniques. Results show that these techniques improve decision-making efficiency and confidence while underscoring the need for better data preparation, risk assessment, and domain knowledge integration support. Finally, we offer design recommendations to enhance future business analytics systems.

cs.HC↗

arXiv2024

Mind the Data Gap: Bridging LLMs to Enterprise Data Integration

Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to uplift the performance of LLMs on enterprise data, including (1) hierarchical annotation, (2) runtime class-learning, and (3) ontology synthesis. We show that, once these techniques are deployed, the performance on enterprise data becomes on par with that of public data. The Goby benchmark can be obtained at https://goby-benchmark.github.io/.

cs.DB↗

arXiv2024

Humboldt: Metadata-Driven Extensible Data Discovery

Data discovery is crucial for data management and analysis and can benefit from better utilization of metadata. For example, users may want to search data using queries like ``find the tables created by Alex and endorsed by Mike that contain sales numbers.'' They may also want to see how the data they view relates to other data, its lineage, or the quality and compliance of its upstream datasets, all metadata. Yet, effectively surfacing metadata through interactive user interfaces (UIs) to augment data discovery poses challenges. Constantly revamping UIs with each update to metadata sources (or providers) consumes significant development resources and lacks scalability and extensibility. In response, we introduce Humboldt, a new framework enabling interactive data systems to effectively leverage metadata for data discovery and rapidly evolve their UIs to support metadata changes. Humboldt decouples metadata sources from the implementation of data discovery UIs that support search and dataset visualization using metadata fields. It automatically generates interactive data discovery interfaces from declarative specifications, avoiding costly metadata-specific (re)implementations.

cs.DB↗

arXiv2024

Making LLMs Work for Enterprise Data Tasks

Large language models (LLMs) know little about enterprise database tables in the private data ecosystem, which substantially differ from web text in structure and content. As LLMs' performance is tied to their training data, a crucial question is how useful they can be in improving enterprise database management and analysis tasks. To address this, we contribute experimental results on LLMs' performance for text-to-SQL and semantic column-type detection tasks on enterprise datasets. The performance of LLMs on enterprise data is significantly lower than on benchmark datasets commonly used. Informed by our findings and feedback from industry practitioners, we identify three fundamental challenges -- latency, cost, and quality -- and propose potential solutions to use LLMs in enterprise data workflows effectively.

cs.DB↗

arXiv2023

AdaTyper: Adaptive Semantic Column Type Detection

Understanding the semantics of relational tables is instrumental for automation in data exploration and preparation systems. A key source for understanding a table is the semantics of its columns. With the rise of deep learning, learned table representations are now available, which can be applied for semantic type detection and achieve good performance on benchmarks. Nevertheless, we observe a gap between this performance and its applicability in practice. In this paper, we propose AdaTyper to address one of the most critical deployment challenges: adaptation. AdaTyper uses weak-supervision to adapt a hybrid type predictor towards new semantic types and shifted data distributions at inference time, using minimal human feedback. The hybrid type predictor of AdaTyper combines rule-based methods and a light machine learning model for semantic column type detection. We evaluate the adaptation performance of AdaTyper on real-world database tables hand-annotated with semantic column types through crowdsourcing and find that the f1-score improves for new and existing types. AdaTyper approaches an average precision of 0.6 after only seeing 5 examples, significantly outperforming existing adaptation methods based on human-provided regular expressions or dictionaries.

cs.DB↗

arXiv2023

VegaProf: Profiling Vega Visualizations

Domain-specific languages (DSLs) for visualization aim to facilitate visualization creation by providing abstractions that offload implementation and execution details from users to the system layer. Therefore, DSLs often execute user-defined specifications by transforming them into intermediate representations (IRs) in successive lowering operations. However, DSL-specified visualizations can be difficult to profile and, hence, optimize due to the layered abstractions. To better understand visualization profiling workflows and challenges, we conduct formative interviews with visualization engineers who use Vega in production. Vega is a popular visualization DSL that transforms specifications into dataflow graphs, which are then executed to render visualization primitives. Our formative interviews reveal that current developer tools are ill-suited for visualization profiling since they are disconnected from the semantics of Vega's specification and its IRs at runtime. To address this gap, we introduce VegaProf, the first performance profiler for Vega visualizations. VegaProf instruments the Vega library by associating a declarative specification with its compilation and execution. Integrated into a Vega code playground, VegaProf coordinates visual performance inspection at three abstraction levels: function, dataflow graph, and visualization specification. We evaluate VegaProf through use cases and feedback from visualization engineers as well as original developers of the Vega library. Our results suggest that VegaProf makes visualization profiling more tractable and actionable by enabling users to interactively probe time performance across layered abstractions of Vega. Furthermore, we distill recommendations from our findings and advocate for co-designing visualization DSLs together with their introspection tools.

cs.HC↗

arXiv2023

Data Extraction via Semantic Regular Expression Synthesis

Many data extraction tasks of practical relevance require not only syntactic pattern matching but also semantic reasoning about the content of the underlying text. While regular expressions are very well suited for tasks that require only syntactic pattern matching, they fall short for data extraction tasks that involve both a syntactic and semantic component. To address this issue, we introduce semantic regexes, a generalization of regular expressions that facilitates combined syntactic and semantic reasoning about textual data. We also propose a novel learning algorithm that can synthesize semantic regexes from a small number of positive and negative examples. Our proposed learning algorithm uses a combination of neural sketch generation and compositional type-directed synthesis for fast and effective generalization from a small number of examples. We have implemented these ideas in a new tool called Smore and evaluated it on representative data extraction tasks involving several textual datasets. Our evaluation shows that semantic regexes can better support complex data extraction tasks than standard regular expressions and that our learning algorithm significantly outperforms existing tools, including state-of-the-art neural networks and program synthesis tools.

cs.PL↗

arXiv2023

GitTables: A Large-Scale Corpus of Relational Tables

The success of deep learning has sparked interest in improving relational table tasks, like data preparation and search, with table representation models trained on large table corpora. Existing table corpora primarily contain tables extracted from HTML pages, limiting the capability to represent offline database tables. To train and evaluate high-capacity models for applications beyond the Web, we need resources with tables that resemble relational database tables. Here we introduce GitTables, a corpus of 1M relational tables extracted from GitHub. Our continuing curation aims at growing the corpus to at least 10M tables. Analyses of GitTables show that its structure, content, and topical coverage differ significantly from existing table corpora. We annotate table columns in GitTables with semantic types, hierarchical relations and descriptions from Schema.org and DBpedia. The evaluation of our annotation pipeline on the T2Dv2 benchmark illustrates that our approach provides results on par with human annotations. We present three applications of GitTables, demonstrating its value for learned semantic type detection models, schema completion methods, and benchmarks for table-to-KG matching, data search, and preparation. We make the corpus and code available at https://gittables.github.io.

cs.DB↗

arXiv2023

WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses

Data discovery is a major challenge in enterprise data analysis: users often struggle to find data relevant to their analysis goals or even to navigate through data across data sources, each of which may easily contain thousands of tables. One common user need is to discover tables joinable with a given table. This need is particularly critical because join is a ubiquitous operation in data analysis, and join paths are mostly obscure to users, especially across databases. Furthermore, users are typically interested in finding ``semantically'' joinable tables: with columns that can be transformed to become joinable even if they are not joinable as currently represented in the data store. We present WarpGate, a system prototype for data discovery over cloud data warehouses. WarpGate implements an embedding-based solution to semantic join discovery, which encodes columns into high-dimensional vector space such that joinable columns map to points that are near each other. Through experiments on several table corpora, we show that WarpGate (i) captures semantic relationships between tables, especially those across databases, and (ii) is sample efficient and thus scalable to very large tables of millions of rows. We also showcase an application of WarpGate within an enterprise product for cloud data analytics.

cs.DB↗

arXiv2022

Transactions Make Debugging Easy

We propose TROD, a novel transaction-oriented framework for debugging modern distributed web applications and online services. Our critical insight is that if applications store all state in databases and only access state transactionally, TROD can use lightweight always-on tracing to track the history of application state changes and data provenance, and then leverage the captured traces and transaction logs to faithfully replay or even test modified code retroactively on any past event. We demonstrate how TROD can simplify programming and debugging in production applications, list several research challenges and directions, and encourage the database and systems communities to drastically rethink the synergy between the way people develop and debug applications.

cs.DB↗

arXiv2022

Sigma Workbook: A Spreadsheet for Cloud Data Warehouses

Cloud data warehouses (CDWs) bring large-scale data and compute power closer to users in enterprises. However, existing tools for analyzing data in CDWs are either limited in ad-hoc transformations or difficult to use for business users. Here we introduce Sigma Workbook, a new interactive system that enables business users to easily perform a visual analysis of data in CDWs at scale. For this, Sigma Workbook provides an accessible spreadsheet-like interface for analysis through direct manipulation. Sigma Workbook dynamically constructs matching SQL queries from user interactions, building on the versatility and expressivity of SQL. Constructed queries are directly executed on CDWs, leveraging the superior characteristics of the new generation CDWs, including scalability. We demonstrate Sigma Workbook through 3 real-life use cases -- cohort analysis, sessionization, and data augmentation -- and underline Workbook's ease of use, scalability, and expressivity.

cs.DB↗

arXiv2022

Machine Learning with DBOS

We recently proposed a new cluster operating system stack, DBOS, centered on a DBMS. DBOS enables unique support for ML applications by encapsulating ML code within stored procedures, centralizing ancillary ML data, providing security built into the underlying DBMS, co-locating ML code and data, and tracking data and workflow provenance. Here we demonstrate a subset of these benefits around two ML applications. We first show that image classification and object detection models using GPUs can be served as DBOS stored procedures with performance competitive to existing systems. We then present a 1D CNN trained to detect anomalies in HTTP requests on DBOS-backed web services, achieving SOTA results. We use this model to develop an interactive anomaly detection system and evaluate it through qualitative user feedback, demonstrating its usefulness as a proof of concept for future work to develop learned real-time security services on top of DBOS.

cs.CR↗

arXiv2022

Annotating Columns with Pre-trained Language Models

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.

cs.DB↗

arXiv2022

Augmenting Decision Making via Interactive What-If Analysis

The fundamental goal of business data analysis is to improve business decisions using data. Business users often make decisions to achieve key performance indicators (KPIs) such as increasing customer retention or sales, or decreasing costs. To discover the relationship between data attributes hypothesized to be drivers and those corresponding to KPIs of interest, business users currently need to perform lengthy exploratory analyses. This involves considering multitudes of combinations and scenarios and performing slicing, dicing, and transformations on the data accordingly, e.g., analyzing customer retention across quarters of the year or suggesting optimal media channels across strata of customers. However, the increasing complexity of datasets combined with the cognitive limitations of humans makes it challenging to carry over multiple hypotheses, even for simple datasets. Therefore mentally performing such analyses is hard. Existing commercial tools either provide partial solutions or fail to cater to business users altogether. Here we argue for four functionalities to enable business users to interactively learn and reason about the relationships between sets of data attributes thereby facilitating data-driven decision making. We implement these functionalities in SystemD, an interactive visual data analysis system enabling business users to experiment with the data by asking what-if questions. We evaluate the system through three business use cases: marketing mix modeling, customer retention analysis, and deal closing analysis, and report on feedback from multiple business users. Users find the SystemD functionalities highly useful for quick testing and validation of their hypotheses around their KPIs of interest, addressing their unmet analysis needs. The feedback also suggests that the UX design can be enhanced to further improve the understandability of these functionalities.

cs.DB↗

arXiv2021

Making Table Understanding Work in Practice

Understanding the semantics of tables at scale is crucial for tasks like data integration, preparation, and search. Table understanding methods aim at detecting a table's topic, semantic column types, column relations, or entities. With the rise of deep learning, powerful models have been developed for these tasks with excellent accuracy on benchmarks. However, we observe that there exists a gap between the performance of these models on these benchmarks and their applicability in practice. In this paper, we address the question: what do we need for these models to work in practice? We discuss three challenges of deploying table understanding models and propose a framework to address them. These challenges include 1) difficulty in customizing models to specific domains, 2) lack of training data for typical database tables often found in enterprises, and 3) lack of confidence in the inferences made by models. We present SigmaTyper which implements this framework for the semantic column type detection task. SigmaTyper encapsulates a hybrid model trained on GitTables and integrates a lightweight human-in-the-loop approach to customize the model. Lastly, we highlight avenues for future research that further close the gap towards making table understanding effective in practice.

cs.DB↗

arXiv2021

TagRuler: Interactive Tool for Span-Level Data Programming by Demonstration

Despite rapid developments in the field of machine learning research, collecting high-quality labels for supervised learning remains a bottleneck for many applications. This difficulty is exacerbated by the fact that state-of-the-art models for NLP tasks are becoming deeper and more complex, often increasing the amount of training data required even for fine-tuning. Weak supervision methods, including data programming, address this problem and reduce the cost of label collection by using noisy label sources for supervision. However, until recently, data programming was only accessible to users who knew how to program. To bridge this gap, the Data Programming by Demonstration framework was proposed to facilitate the automatic creation of labeling functions based on a few examples labeled by a domain expert. This framework has proven successful for generating high-accuracy labeling models for document classification. In this work, we extend the DPBD framework to span-level annotation tasks, arguably one of the most time-consuming NLP labeling tasks. We built a novel tool, TagRuler, that makes it easy for annotators to build span-level labeling functions without programming and encourages them to explore trade-offs between different labeling models and active learning strategies. We empirically demonstrated that an annotator could achieve a higher F1 score using the proposed tool compared to manual labeling for different span-level annotation tasks.

cs.CL↗