Tianjing Zeng

Yunxiang Su, Tianjing Zeng, Zhongjun Ding et al.

With the development of large language models (LLMs), numerous studies integrate LLMs through operator-like components to enhance relational data processing tasks, e.g., filters with semantic predicates, knowledge-augmented table imputation, reasoning-driven entity matching and more challenging semantic query processing. These components invoke LLMs while preserving a relational input/output interface, which we refer to as LLM-Enhanced Relational Operators (LROs). From an operator perspective, unfortunately, these existing LROs suffer from fragmented definition, various implementation strategies and inadequate evaluation benchmarks. To this end, in this paper, we first establish a unified LRO taxonomy to align existing LROs, and categorize them into: Select, Match, Impute, Cluster and Order, along with their operands and implementation variants. Second, we design LROBench, a comprehensive benchmark featuring 290 single-LRO queries and 60 multi-LRO queries, spanning 27 databases across more than 10 domains. LROBench covers all operating logics and operand granularities in its single-LRO workload, and provides challenging multi-LRO queries stratified by query complexity. Based on these, we evaluate individual LROs under various implementations, deriving practical insights into LRO design choices and summarizing our empirical best practices. We further compare the end-to-end performance of existing multi-LRO systems against an LRO suite instantiated with these best practices, in order to investigate how to design an effective LRO set for multi-LRO systems targeting complex semantic queries. Last, to facilitate future work, we outline promising future directions and open-source all benchmark data and evaluation code, available at https://github.com/LROBench/LROBench/.

Zhongjun Ding, Yin Lin, Tianjing Zeng

Text-to-SQL systems translate natural language questions into SQL queries, providing substantial value for non-expert users. While large language models (LLMs) show promising results for this task, they remain error-prone. Query ambiguity has been recognized as a major obstacle for LLM-based Text-to-SQL systems, leading to misinterpretation of user intent and inaccurate SQL generation. We demonstrate AmbiSQL, an interactive system that automatically detects query ambiguities and guides users through intuitive multiple-choice questions to clarify their intent. Our approach introduces a fine-grained ambiguity taxonomy for identifying ambiguities that affect database element mapping and LLM reasoning, then incorporates user feedback to rewrite ambiguous questions. Evaluation on an ambiguous query dataset shows that AmbiSQL achieves 87.2% precision in ambiguity detection and improves SQL exact match accuracy by 50% when integrated with Text-to-SQL systems. Our demonstration showcases the significant performance gains and highlights the system's practical usability. Code repo and demonstration are available at: https://github.com/JustinzjDing/AmbiSQL.

Tianjing Zeng, Junwei Lan, Jiahong Ma et al.

Cardinality estimation (CardEst) is essential for optimizing query execution plans. Recent ML-based CardEst methods achieve high accuracy but face deployment challenges due to high preparation costs and lack of transferability across databases. In this paper, we propose PRICE, a PRetrained multI-table CardEst model, which addresses these limitations. PRICE takes low-level but transferable features w.r.t. data distributions and query information and elegantly applies self-attention models to learn meta-knowledge to compute cardinality in any database. It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods. Moreover, PRICE can be finetuned to further enhance its performance on any specific database. We pretrained PRICE using 30 diverse datasets, completing the process in about 5 hours with a resulting model size of only about 40MB. Evaluations show that PRICE consistently outperforms existing methods, achieving the highest estimation accuracy on several unseen databases and generating faster execution plans with lower overhead. After finetuning with a small volume of databasespecific queries, PRICE could even find plans very close to the optimal ones. Meanwhile, PRICE is generally applicable to different settings such as data updates, data scaling, and query workload shifts. We have made all of our data and codes publicly available at https://github.com/StCarmen/PRICE.

Andreas Pfadler, Rong Zhu, Wei Chen et al.

We present Baihe, a SysML Framework for AI-driven Databases. Using Baihe, an existing relational database system may be retrofitted to use learned components for query optimization or other common tasks, such as e.g. learned structure for indexing. To ensure the practicality and real world applicability of Baihe, its high level architecture is based on the following requirements: separation from the core system, minimal third party dependencies, Robustness, stability and fault tolerance, as well as stability and configurability. Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers. To serve both practitioners, as well as researchers in the DB and AI4DB community Baihe for PostgreSQL will be released under open source license.

Yin Lin, Tianjing Zeng, Zhongjun Ding et al.

Relational databases excel at structured data analysis, but real-world queries increasingly require capabilities beyond standard SQL, such as semantically matching entities across inconsistent names, extracting information not explicitly stored in schemas, and analyzing unstructured text. While text-to-SQL systems enable natural language querying, they remain limited to relational operations and cannot leverage the semantic reasoning capabilities of modern large language models (LLMs). Conversely, recent semantic operator systems extend relational algebra with LLM-powered operations (e.g., semantic joins, mappings, aggregations), but require users to manually construct complex query pipelines. To address this gap, we present SEMA-SQL, a system that automatically answers natural language questions by generating efficient queries that combine relational operations with LLM semantic reasoning. We formalize Hybrid Relational Algebra (HRA), a declarative abstraction unifying traditional relational operators with LLM user-defined functions (UDFs). The system automates three critical aspects: (1) query generation via in-context learning that produces HRA queries with precise natural language specifications for LLM UDFs, (2) query optimization via cost-based transformations and UDF rewriting, and (3) efficient execution algorithms that reduce LLM invocations by an average of 93% in semantic joins through intelligent batching. Extensive experiments with known benchmarks, and extensions thereof, demonstrate the significant query capability improvements possible with our design.

Rong Zhu, Tianjing Zeng, Andreas Pfadler et al.

Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS. The CardEst problem has been extensively studied in the last several decades, using both traditional and ML-enhanced methods. Whereas, the hardest problem in CardEst, i.e., how to estimate the join query size on multiple tables, has not been extensively solved. Current methods either reply on independence assumptions or apply techniques with heavy burden, whose performance is still far from satisfactory. Even worse, existing CardEst methods are often designed to optimize one goal, i.e., inference speed or estimation accuracy, which can not adapt to different occasions. In this paper, we propose a very general framework, called Glue, to tackle with these challenges. Its key idea is to elegantly decouple the correlations across different tables and losslessly merge single table CardEst results to estimate the join query size. Glue supports obtaining the single table-wise CardEst results using any existing CardEst method and can process any complex join schema. Therefore, it easily adapts to different scenarios having different performance requirements, i.e., OLTP with fast estimation time or OLAP with high estimation accuracy. Meanwhile, we show that Glue can be seamlessly integrated into the plan search process and is able to support counting distinct number of values. All these properties exhibit the potential advances of deploying Glue in real-world DBMS.