1 citations · 1 across the 7 of their papers we have counts for
7 papers
Compositional Online Learning for Semantic Data Processing Systems
Paweł Liskowski, Fuheng Zhao, Benjamin Han +2
An LLM call in a semantic data processing system is expensive enough to dominate query cost, yet slow enough to hide a CPU-side learner's update behind its round-trip. In productio…
Larch: Learned Query Optimization for Semantic Predicates
Fuheng Zhao, Pawel Liskowski, Zihan Li +5
With the advent of Large Language Models (LLMs), many database systems introduced semantic operators that enabled analytical queries over unstructured data (e.g. text, images, vide…
AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery
Darek Kleczek, Fuheng Zhao, Alexander W. Lee +4
We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. F…
Streaming Model Cascades for Semantic SQL
Paweł Liskowski, Kyle Schmaus
Modern data warehouses extend SQL with semantic operators that invoke large language models on each qualifying row, making per-row inference orders of magnitude more expensive than…
Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
Paweł Liskowski, Krzysztof Jankowski
We introduce Arctic-ABSA, a collection of powerful models for real-life aspect-based sentiment analysis (ABSA). Our models are tailored to commercial needs, trained on a large corp…
Cortex AISQL: A Production SQL Engine for Unstructured Data
Paweł Liskowski, Benjamin Han, Paritosh Aggarwal +11
Snowflake's Cortex AISQL is a production SQL engine that integrates native semantic operations directly into SQL. This integration allows users to write declarative queries that co…
Arctic-TILT. Business Document Understanding at Sub-Billion Scale
Łukasz Borchmann, Michał Pietruszka, Wojciech Jaśkowski +13
The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\…