相关论文: SemanticAgent: A Semantics-Aware Framework for Tex…

Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments. The primary limitation lies in their reliance on static schema representations, which fails to…

This paper develops a new framework for program synthesis, called semantics-guided synthesis (SemGuS), that allows a user to provide both the syntax and the semantics for the constructs in the language. SemGuS accepts a recursively defined…

The complexity of SQL and the spatial semantics of PostGIS create barriers for non-experts working with spatial data. Although large language models can translate natural language into SQL, spatial Text-to-SQL is more error-prone than…

Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained…

High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete,…

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

The increasing focus on Web 3.0 is leading to automated creation and enrichment of ontologies and other linked datasets. Alongside automation, quality evaluation of enriched ontologies can impact software reliability and reuse. Current…

Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training.…

We introduce the task of text-to-diagram generation, which focuses on creating structured visual representations directly from textual descriptions. Existing approaches in text-to-image and text-to-code generation lack the logical…

The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which…

Evaluating Text-to-SQL agents in private business intelligence (BI) settings is challenging due to the scarcity of realistic, domain-specific data. While synthetic evaluation data offers a scalable solution, existing generation methods fail…

The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narration. However, existing automated methods primarily focus…

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical…

We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training costs and understanding-generation trade-offs, GenAgent decouples these capabilities…

Evaluating text-to-SQL systems remains largely fragile: correctness is typically judged by executing predicted and gold SQL queries on a single static database, even though the same queries may behave differently under alternative database…

Large Language Models have recently shown impressive capabilities in reasoning and code generation, making them promising tools for natural language interfaces to relational databases. However, existing approaches often fail to generalize…

Training effective Text-to-SQL models remains challenging due to the scarcity of high-quality, diverse, and structurally complex datasets. Existing methods either rely on limited human-annotated corpora, or synthesize datasets directly by…

Text-to-SQL bridges the gap between natural language and structured database language, thus allowing non-technical users to easily query databases. Traditional approaches model text-to-SQL as a direct translation task, where a given Natural…

Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did…

Data annotation remains a significant bottleneck in the Humanities and Social Sciences, particularly for complex semantic tasks such as metaphor identification. While Large Language Models (LLMs) show promise, a significant gap remains…