Cover Image

Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeighami, Sepanta, Shankar, Shreya, Parameswaran, Aditya
Format:	Preprint
Published:	2025
Subjects:	Databases Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM-Powered Proactive Data Systems
by: Zeighami, Sepanta, et al.
Published: (2025)

Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees
by: Zeighami, Sepanta, et al.
Published: (2025)

Task Cascades for Efficient Unstructured Data Processing
by: Shankar, Shreya, et al.
Published: (2026)

Semantic Data Processing with Holistic Data Understanding
by: Sun, Youran, et al.
Published: (2026)

Arming Data Agents with Tribal Knowledge
by: Agarwal, Shubham, et al.
Published: (2026)

Multi-Objective Agentic Rewrites for Unstructured Data Processing
by: Wei, Lindsey Linxi, et al.
Published: (2025)

RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines
by: Lauro, Quentin Romero, et al.
Published: (2025)

DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
by: Shankar, Shreya, et al.
Published: (2024)

Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
by: Liu, Shu, et al.
Published: (2025)

Towards Establishing Guaranteed Error for Learned Database Operations
by: Zeighami, Sepanta, et al.
Published: (2024)

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
by: Zeighami, Sepanta, et al.
Published: (2024)

Can AI Agents Answer Your Data Questions? A Benchmark for Data Agents
by: Ma, Ruiying, et al.
Published: (2026)

BiasBuster: a Neural Approach for Accurate Estimation of Population Statistics using Biased Location Data
by: Zeighami, Sepanta, et al.
Published: (2024)

Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability
by: Zeighami, Sepanta, et al.
Published: (2024)

Towards Accurate and Efficient Document Analytics with Large Language Models
by: Lin, Yiming, et al.
Published: (2024)

SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees
by: Jo, Saehan, et al.
Published: (2024)

Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism
by: Kapenekakis, Antheas, et al.
Published: (2026)

TARGET: Benchmarking Table Retrieval for Generative Tasks
by: Ji, Xingyu, et al.
Published: (2025)

Steering Semantic Data Processing With DocWrangler
by: Shankar, Shreya, et al.
Published: (2025)

DataLab: A Unified Platform for LLM-Powered Business Intelligence
by: Weng, Luoxuan, et al.
Published: (2024)

TableNet A Large-Scale Table Dataset with LLM-Powered Autonomous
by: Zhang, Ruilin, et al.
Published: (2026)

LLM/Agent-as-Data-Analyst: A Survey
by: Tang, Zirui, et al.
Published: (2025)

Powering In-Database Dynamic Model Slicing for Structured Data Analytics
by: Zeng, Lingze, et al.
Published: (2024)

Interactive Data Harmonization with LLM Agents: Opportunities and Challenges
by: Santos, Aécio, et al.
Published: (2025)

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
by: Shankar, Shreya, et al.
Published: (2024)

CoddLLM: Empowering Large Language Models for Data Analytics
by: Zhang, Jiani, et al.
Published: (2025)

A System and Benchmark for LLM-based Q&A on Heterogeneous Data
by: Fokoue, Achille, et al.
Published: (2024)

ARCADE: A Real-Time Data System for Hybrid and Continuous Query Processing across Diverse Data Modalities
by: Yang, Jingyi, et al.
Published: (2025)

OCPM$^2$: Extending the Process Mining Methodology for Object-Centric Event Data Extraction
by: Miri, Najmeh, et al.
Published: (2025)

Real-Time Health Analytics Using Ontology-Driven Complex Event Processing and LLM Reasoning: A Tuberculosis Case Study
by: Chandra, Ritesh, et al.
Published: (2025)

FlexiDataGen: An Adaptive LLM Framework for Dynamic Semantic Dataset Generation in Sensitive Domains
by: Jelodar, Hamed, et al.
Published: (2025)

Bootstrapping Learned Cost Models with Synthetic SQL Queries
by: Nidd, Michael, et al.
Published: (2025)

DFIN-SQL: Integrating Focused Schema with DIN-SQL for Superior Accuracy in Large-Scale Databases
by: Volvovsky, Shai, et al.
Published: (2024)

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
by: Tang, Zirui, et al.
Published: (2025)

CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation
by: Zhang, Kaixin, et al.
Published: (2024)

Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data
by: Li, Ruyu, et al.
Published: (2026)

Efficient Distance Pruning for Process Suffix Comparison in Prescriptive Process Monitoring
by: Madad, Sarra
Published: (2026)

Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!
by: Allemang, Dean, et al.
Published: (2024)

Autonomous Data Processing using Meta-Agents
by: Khurana, Udayan
Published: (2026)

Deterministic Preprocessing and Interpretable Fuzzy Banding for Cost-per-Student Reporting from Extracted Records
by: Lee, Shane, et al.
Published: (2026)