Related papers: Database Normalization via Dual-LLM Self-Refinemen…

We investigate the problem of aligning two RDF databases, an essential problem in understanding the evolution of ontologies. Our approaches address three fundamental challenges: 1) the use of "blank" (null) names, 2) ontology changes in…

Relational databases play a central role in many information systems. Their schema contains structural (e.g. tables and columns) and behavioral (e.g. stored procedures or views) entity descriptions. Then, just like for ``normal'' software,…

Interpreting data is central to modern research. Large language models (LLMs) show promise in providing such natural language interpretations of data, yet simple feature extraction methods such as prompting often fail to produce accurate…

Software correctness is ensured mathematically through formal verification, which involves the resources of generating formal requirement specifications and having an implementation that must be verified. Tools such as model-checkers and…

Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language…

Relational database management systems (RDBMSs) are powerful because they are able to optimize and answer queries against any relational database. A natural language interface (NLI) for a database, on the other hand, is tailored to support…

Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and…

Big data analytics is gaining massive momentum in the last few years. Applying machine learning models to big data has become an implicit requirement or an expectation for most analysis tasks, especially on high-stakes applications.Typical…

Database de-anonymization typically involves matching an anonymized database with correlated publicly available data. Existing research focuses either on practical aspects without requiring knowledge of the data distribution yet provides…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning,…

In the rapidly evolving AI era with large language models (LLMs) at the core, making LLMs more trustworthy and efficient, especially in output generation (inference), has gained significant attention. This is to reduce plausible but faulty…

Careful curation of data sources can significantly improve the performance of LLM pre-training, but predominant approaches rely heavily on intuition or costly trial-and-error, making them difficult to generalize across different data…

Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models.…

An applied problem facing all areas of data science is harmonizing data sources. Joining data from multiple origins with unmapped and only partially overlapping features is a prerequisite to developing and testing robust, generalizable…

We present Mirror, an open-source platform for data exploration and analysis powered by large language models. Mirror offers an intuitive natural language interface for querying databases, and automatically generates executable SQL commands…

We present FinAI Data Assistant, a practical approach for natural-language querying over financial databases that combines large language models (LLMs) with the OpenAI Function Calling API. Rather than synthesizing complete SQL via…

Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on how the batches are constructed during training and it may not…

Feature transformation aims to reconstruct the feature space of raw features to enhance the performance of downstream models. However, the exponential growth in the combinations of features and operations poses a challenge, making it…

With the exponential increase in online scientific literature, identifying reliable domain-specific data has become increasingly important but also very challenging. Manual data collection and filtering for domain-specific scientific…

Many web databases can be seen as providing partial and overlapping information about entities in the world. To answer queries effectively, we need to integrate the information about the individual entities that are fragmented over multiple…