paper-with-me

홈 › Papers

Abacus: A Cost-Based Optimizer for Semantic Operator Systems

2025-05-20 · Matthew Russo, Sivaprasad Sudhir, Gerardo Vitagliano, Chunwei Liu, Tim Kraska, Samuel Madden, Michael Cafarella

LLMs enable an exciting new class of data processing applications over large collections of unstructured documents. Several new programming frameworks have enabled developers to build these applications by composing them out of semantic operators: a declarative set of AI-powered data transformations with natural language specifications. These include LLM-powered maps, filters, joins, etc. used for document processing tasks such as information extraction, summarization, and more. While systems of semantic operators have achieved strong performance on benchmarks, they can be difficult to optimize. An optimizer for this setting must determine how to physically implement each semantic operator in a way that optimizes the system globally. Existing optimizers are limited in the number of optimizations they can apply, and most (if not all) cannot optimize system quality, cost, or latency subject to constraint(s) on the other dimensions. In this paper we present Abacus, an extensible, cost-based optimizer which searches for the best implementation of a semantic operator system given a (possibly constrained) optimization objective. Abacus estimates operator performance by leveraging a minimal set of validation examples and, if available, prior beliefs about operator performance. We evaluate Abacus on document processing workloads in the biomedical and legal domains (BioDEX; CUAD) and multi-modal question answering (MMQA). We demonstrate that systems optimized by Abacus achieve 18.7%-39.2% better quality and up to 23.6x lower cost and 4.2x lower latency than the next best system.

📄 PDF Abstract BibTeX arXiv:2505.14661

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization

2025-11-25 · Junhao Zhu, Lu Chen, Xiangyu Ke, Ziquan Fang 외 arxiv

Multi-modal analytical processing has the potential to transform applications in e-commerce, healthcare, entertainment, and beyond. However, real-world adoption remains elusive due to the limited ability of traditional r…

ABACUS: A FinOps Service for Cloud Cost Optimization

2024-12-22 · Saurabh Deochake

In recent years, as more enterprises have moved their infrastructure to the cloud, significant challenges have emerged in achieving holistic cloud spend visibility and cost optimization. FinOps practices provide a way fo…

Blocking

A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumeration

2021-01-05 · Hai Lan, Zhifeng Bao, Yuwei Peng

Query optimizer is at the heart of the database systems. Cost-based optimizer studied in this paper is adopted in almost all current database systems. A cost-based optimizer introduces a plan enumeration algorithm to fin…

Access Paths for Efficient Ordering with Large Language Models

2025-08-30 · Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani 외 arxiv

In this work, we present the \texttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical implementations. First, we propose several improvements to existing semantic so…

Abacus: Self-Supervised Event Counting-Aligned Distributional Pretraining for Sequential User Modeling

2025-12-18 · Sullivan Castro, Artem Betlei, Thomas Di Martino, Nadir El Manouzi arxiv

Modeling user purchase behavior is a critical challenge in display advertising systems, necessary for real-time bidding. The difficulty arises from the sparsity of positive user events and the stochasticity of user actio…