Related papers: Companion Agents: A Table-Information Mining Parad…

Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, proprietary, and unstructured corpora during live interactions…

Database theory is exciting because it studies highly general and practically useful abstractions. Conjunctive query (CQ) evaluation is a prime example: it simultaneously generalizes graph pattern matching, constraint satisfaction, and…

Efficient querying and analysis of large tabular datasets remain significant challenges, especially for users without expertise in programming languages like SQL. Text-to-SQL approaches have shown promising performance on benchmark data;…

Text-to-SQL aims to translate natural language queries into SQL statements, which is practical as it enables anyone to easily retrieve the desired information from databases. Recently, many existing approaches tackle this problem with Large…

We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing…

Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric datasets in a meaningful way across heterogeneous feature spaces. Existing approaches…

Transforming fragmented enterprise data into actionable insights remains a significant challenge for LLMs, constrained by complex database schemas, limitations in dynamic SQL generation, and the need for deep multi-dimensional analysis.In…

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the…

Recent advancements in AI-driven conversational agents have exhibited immense potential of AI applications. Effective response generation is crucial to the success of these agents. While extensive research has focused on leveraging multiple…

Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information.…

Open-domain table question answering traditionally relies on a two-stage pipeline: static table retrieval followed by a closed-domain answer. In contrast, we propose an end-to-end agentic framework that embeds multi-turn tool calls-using a…

Aggregation query over free text is a long-standing yet underexplored problem. Unlike ordinary question answering, aggregate queries require exhaustive evidence collection and systems are required to "find all," not merely "find one."…

Text-to-SQL benchmarks play a crucial role in evaluating the progress made in the field and the ranking of different models. However, accurately matching a model-generated SQL query to a reference SQL query in a benchmark fails for various…

Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignment problem. In traditional paradigms, rewards are determined…

While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists where syntactically valid queries often misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a novel…

Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to multi-system data backends surfaces a harder problem: the search space is heterogeneous,…

Relation extraction (RE) tasks show promising performance in extracting relations from two entities mentioned in sentences, given sufficient annotations available during training. Such annotations would be labor-intensive to obtain in…

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale,…

Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical…