Weaver: Interweaving SQL and LLM for Table Reasoning

• URL: http://arxiv.org/abs/2505.18961v2
• Date: Tue, 23 Sep 2025 18:02:45 GMT
• Title: Weaver: Interweaving SQL and LLM for Table Reasoning
• Authors: Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, Vivek Gupta,
• Abstract summary: Weaver generates a flexible, step-by-step plan that combinessql for structured data retrieval with LLMs for semantic processing.<n>Weaver consistently outperforms state-of-the-art methods across four TableQA datasets.
• Score: 62.55797244714265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Querying tables with unstructured data is challenging due to the presence of text (or image), either embedded in the table or in external paragraphs, which traditional SQL struggles to process, especially for tasks requiring semantic reasoning. While Large Language Models (LLMs) excel at understanding context, they face limitations with long input sequences. Existing approaches that combine SQL and LLMs typically rely on rigid, predefined work-flows, limiting their adaptability to complex queries. To address these issues, we introduce Weaver , a modular pipeline that dynamically integrates SQL and LLMs for table-based question answering (TableQA). Weaver generates a flexible, step-by-step plan that combines SQL for structured data retrieval with LLMs for semantic processing. By decomposing complex queries into manageable subtasks, Weaver improves accuracy and generalization. Our experiments show that Weaver consistently outperforms state-of-the-art methods across four TableQA datasets, reducing both API calls and error rates. The code, along with other associated scripts, are available at https://coral-lab-asu.github.io/weaver.

Related papers

• CORE-T: COherent REtrieval of Tables for Text-to-SQL [91.76918495375384]
  CORE-T is a scalable, training-free framework that enriches tables with purpose metadata and pre-computes a lightweight table-compatibility cache.<n>Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42% fewer tables.
  arXiv  Detail & Related papers  (2026-01-19T14:51:23Z)
• Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration [22.351384833450567]
  Chain-of-Query (CoQ) is a novel multi-agent framework for table understanding.<n>CoQ adopts natural-language-style representations of table schemas to abstract away structural noise and enhance understanding.<n>Experiments across four models and five widely used benchmarks demonstrate that CoQ achieves substantial accuracy improvements.
  arXiv  Detail & Related papers  (2025-08-14T19:46:46Z)
• Improving Table Retrieval with Question Generation from Partial Tables [2.2169618382995764]
  We propose QGpT, a simple yet effective method that uses an LLM to generate synthetic questions based on small portions of a table.<n>The generated questions are then jointly embedded with the partial table segments used for generation, enhancing semantic alignment with user queries.
  arXiv  Detail & Related papers  (2025-08-08T09:35:56Z)
• UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification [50.59009084277447]
  We introduce UNJOIN, a framework that decouples the retrieval of schema elements from logic generation.<n>In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name.<n>In the second stage, the query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic.
  arXiv  Detail & Related papers  (2025-05-23T17:28:43Z)
• Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types [11.391598870596392]
  Large language models (LLMs) have significantly advanced text-to-speech systems.<n>LLMs often narrowly focus on SQL generation, neglecting the complexities of real-world conversational queries.<n>We propose MM, a test suite designed to evaluate the question classification and SQL generation capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-12-21T10:13:45Z)
• Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking [15.42143912008553]
  We introduce a novel, realistic, and sufficiently complex benchmark called SQLEquiQuest for query equivalence checking.<n>We evaluate several state-of-the-art LLMs using various prompting strategies and carefully constructed in-context learning examples.<n>Our analysis shows that LLMs exhibit a strong bias for equivalence predictions, with consistently poor performance over non-equivalent pairs.
  arXiv  Detail & Related papers  (2024-12-07T06:50:12Z)
• BEAVER: An Enterprise Benchmark for Text-to-SQL [5.984348784381797]
  Existing text-to-the-shelf benchmarks have largely been constructed from web tables with human-generated question- pairs.<n>We introduce a new dataset BEA, the first enterprise text-to-the-shelf benchmark sourced from real private enterprise data warehouses.
  arXiv  Detail & Related papers  (2024-09-03T16:37:45Z)
• RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering [11.214912072391108]
  Real-world datasets often feature a vast array of attributes and complex values. Traditional methods cannot fully relay the datasets size and complexity to the Large Language Models. We propose a novel framework that leverages Full-Text Search (FTS) on the input table.
  arXiv  Detail & Related papers  (2024-08-22T13:13:06Z)
• TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools [51.576974932743596]
  Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. TACT contains challenging instructions that demand stitching information scattered across one or more texts. We construct this dataset by leveraging an existing dataset of texts and their associated tables. We demonstrate that all contemporary LLMs perform poorly on this dataset, achieving an accuracy below 38%.
  arXiv  Detail & Related papers  (2024-06-05T20:32:56Z)
• Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion [57.53174887650989]
  Table question answering is a popular task that assesses a model's ability to understand and interact with structured data. Existing methods either convert both the table and external knowledge into text, which neglects the structured nature of the table. We propose a simple yet effective method to integrate external information in a given table.
  arXiv  Detail & Related papers  (2024-01-28T03:37:11Z)
• MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [47.120862170230566]
  Recent Text-to-yourself methods usually suffer from significant performance degradation on "huge" databases.<n>We introduce MAC, a novel Text-to-yourself LLM-based multi-agent collaborative framework.<n>In our framework, we leverage GPT-4 as the strong backbone for all agent tasks to determine the upper bound of our framework.<n>We then fine-tune an open-sourced instruction-followed model,sql-Llama, by leveraging Code 7B, to accomplish all tasks as GPT-4 does.
  arXiv  Detail & Related papers  (2023-12-18T14:40:20Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought [24.1320473171017]
  Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks. We design our chain-of-thought (CoT) prompt with a similar method to schema linking. We extend our in-context learning method to the multi-turn text-to-context task.
  arXiv  Detail & Related papers  (2023-10-26T12:16:25Z)
• Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain [21.593701177605652]
  We propose a Text-to-aware prompting framework, involving a sample and a dynamic revision chain. Our approach incorporates sample demonstrations and fine-grained information related to the given question. To generate executable and accuratesqls without human intervention, we design a dynamic revision chain which iteratively adapts fine-grained feedback.
  arXiv  Detail & Related papers  (2023-07-11T07:16:22Z)
• Weakly Supervised Text-to-SQL Parsing through Question Decomposition [53.22128541030441]
  We take advantage of the recently proposed question meaning representation called QDMR. Given questions, their QDMR structures (annotated by non-experts or automatically predicted) and the answers, we are able to automatically synthesizesql queries. Our results show that the weakly supervised models perform competitively with those trained on NL- benchmark data.
  arXiv  Detail & Related papers  (2021-12-12T20:02:42Z)
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering [78.9863753810787]
  A large amount of world's knowledge is stored in structured databases. query languages can answer questions that require complex reasoning, as well as offering full explainability.
  arXiv  Detail & Related papers  (2021-08-05T22:04:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.