CoddLLM: Empowering Large Language Models for Data Analytics

• URL: http://arxiv.org/abs/2502.00329v1
• Date: Sat, 01 Feb 2025 06:03:55 GMT
• Title: CoddLLM: Empowering Large Language Models for Data Analytics
• Authors: Jiani Zhang, Hengrui Zhang, Rishav Chakravarti, Yiqun Hu, Patrick Ng, Asterios Katsifodimos, Huzefa Rangwala, George Karypis, Alon Halevy,
• Abstract summary: Large Language Models (LLMs) have the potential to revolutionize data analytics. We unveil a new data recipe for post-Turbo synthesiss. We posttrain a new foundation model, named CoddLLM, based on MistralNeMo-12B.
• Score: 38.23203246023766
• License:
• Abstract: Large Language Models (LLMs) have the potential to revolutionize data analytics by simplifying tasks such as data discovery and SQL query synthesis through natural language interactions. This work serves as a pivotal first step toward the development of foundation models explicitly designed for data analytics applications. To propel this vision forward, we unveil a new data recipe for post-training LLMs, enhancing their comprehension of data management and empowering them to tackle complex real-world analytics tasks. Specifically, our innovative approach includes a scalable synthetic data generation method that enables the creation of a broad spectrum of topics centered on data representation and manipulation. Furthermore, we introduce two new tasks that seamlessly bridge tables and text. We show that such tasks can enhance models' understanding of schema creation and the nuanced translation between natural language and tabular data. Leveraging this data recipe, we post-train a new foundation model, named CoddLLM, based on Mistral-NeMo-12B. To assess the language understanding and reasoning capabilities of LLMs in the realm of data analytics, we contribute AnalyticsMMLU, a benchmark containing thousands of multiple-choice questions on databases, data analysis, and machine learning. Our focus on data discovery, has resulted in the contribution of three comprehensive benchmarks that address both database and data lake scenarios. CoddLLM not only excels in performance but also sets a new standard, achieving the highest average accuracy across eight datasets. It outperforms GPT-3.5-Turbo on AnalyticsMMLU, exceeding GPT-4o by 12.1% in table selection and showing an average improvement of 24.9% in Text-to-SQL compared to the base model.

Related papers

• Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models [14.236566119377352]
  This paper presents TiInsight, an automated cross-domain exploratory data analysis system. TiInsight achieves hierarchical execution accuracy of 86.3% on the Spider dataset using GPT-4. It also demonstrates state-of-the-art performance on the Bird dataset.
  arXiv  Detail & Related papers  (2024-12-10T06:11:23Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales. We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• UQE: A Query Engine for Unstructured Databases [71.49289088592842]
  We investigate the potential of Large Language Models to enable unstructured data analytics. We propose a new Universal Query Engine (UQE) that directly interrogates and draws insights from unstructured data collections.
  arXiv  Detail & Related papers  (2024-06-23T06:58:55Z)
• 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)
• GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning [4.8838210812204235]
  In this paper, we propose GeMQuAD - a semi-supervised learning approach, applied to a dataset generated through ICL with just one example in the target language. We iteratively identify high-quality data to enhance model performance, especially for low-resource multilingual setting. Our framework outperforms the machine translation-augmented model by 0.22/1.68 F1/EM points for Hindi and 0.82/1.37 F1/EM points for Spanish on the MLQA dataset.
  arXiv  Detail & Related papers  (2024-04-14T06:55:42Z)
• Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator [63.762209407570715]
  Genixer is a comprehensive data generation pipeline consisting of four key steps. A synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 out of 12 multimodal benchmarks. MLLMs trained with task-specific datasets can surpass GPT-4V in generating complex instruction tuning data.
  arXiv  Detail & Related papers  (2023-12-11T09:44:41Z)
• Exploring the State-of-the-Art Language Modeling Methods and Data Augmentation Techniques for Multilingual Clause-Level Morphology [3.8498574327875947]
  We present our work on all three parts of the shared task: inflection, reinflection, and analysis. We mainly explore two approaches: Transformer models in combination with data augmentation, and exploiting the state-of-the-art language modeling techniques for morphological analysis. Our methods achieved first place in each of the three tasks and outperforms mT5-baseline with 89% for inflection, 80% for reinflection and 12% for analysis.
  arXiv  Detail & Related papers  (2022-11-03T11:53:39Z)

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.