paper-with-me

홈 › Papers

Are Large Language Models the New Interface for Data Pipelines?

2024-06-06 · Sylvio Barbon Junior, Paolo Ceravolo, Sven Groppe, Mustafa Jarrar, Samira Maghool, Florence Sèdes, Soror Sahri, Maurice van Keulen

A Language Model is a term that encompasses various types of models designed to understand and generate human communication. Large Language Models (LLMs) have gained significant attention due to their ability to process text with human-like fluency and coherence, making them valuable for a wide range of data-related tasks fashioned as pipelines. The capabilities of LLMs in natural language understanding and generation, combined with their scalability, versatility, and state-of-the-art performance, enable innovative applications across various AI-related fields, including eXplainable Artificial Intelligence (XAI), Automated Machine Learning (AutoML), and Knowledge Graphs (KG). Furthermore, we believe these models can extract valuable insights and make data-driven decisions at scale, a practice commonly referred to as Big Data Analytics (BDA). In this position paper, we provide some discussions in the direction of unlocking synergies among these technologies, which can lead to more powerful and intelligent AI solutions, driving improvements in data pipelines across a wide range of applications and domains integrating humans, computers, and knowledge.

📄 PDF Abstract BibTeX arXiv:2406.06596

Code (0)

등록된 구현이 없습니다.

Tasks

AutoMLExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Knowledge GraphsLanguage ModelingLanguage ModellingNatural Language Understanding

Similar Papers 제목 키워드 기반

PalimpChat: Declarative and Interactive AI analytics

2025-02-05 · Chunwei Liu, Gerardo Vitagliano, Brandon Rose, Matt Prinz 외

Thanks to the advances in generative architectures and large language models, data scientists can now code pipelines of machine-learning operations to process large collections of unstructured data. Recent progress has s…

scientific discovery

SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines

2026-06-12 · Olga Ovcharenko, Luciano Duarte, Sebastian Schelter arxiv

Machine learning (ML) pipelines require extensive data preparation, feature engineering, and integration across heterogeneous sources, making them tedious and error-prone to develop. While large language models (LLMs) ha…

Feature Engineering

AI for Low-Code for AI

2023-05-31 · Nikitha Rao, Jason Tsay, Kiran Kate, Vincent J. Hellendoorn 외

Low-code programming allows citizen developers to create programs with minimal coding effort, typically via visual (e.g. drag-and-drop) interfaces. In parallel, recent AI-powered tools such as Copilot and ChatGPT generat…

BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab

2020-07-01 · ACL 2020 6 · Yonghao Jin, Fei Li, Hong Yu

CodaLab is an open-source web-based platform for collaborative computational research. Although CodaLab has gained popularity in the research community, its interface has limited support for creating reusable tools that …

Managementnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)

Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols

2026-04-20 · Fernando Reitich arxiv

Large language models are increasingly deployed as protocols: structured multi-call procedures that spend additional computation to transform a baseline answer into a final one. These protocols are evaluated only by end-…