Larch: Learned Query Optimization for Semantic Predicates

• URL: http://arxiv.org/abs/2606.07923v1
• Date: Sat, 06 Jun 2026 01:16:58 GMT
• Title: Larch: Learned Query Optimization for Semantic Predicates
• Abstract summary: We introduce Larch, a framework for optimizing the execution of semantic filters in AI SQL queries.<n>Based on two key observations, we present two Larch variants: Larch-A2C and Larch-Sel.<n>Our results demonstrate that Larch is robust across diverse workloads, reducing total token cost overhead by 3x-19x compared to Palimpzest and Quest.
• Score: 16.10994668093723
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, videos). Semantic operators typically incur high inference costs and latencies making semantic (AI) SQL queries challenging to apply on large scale datasets. At the same time, their semantic nature leads database engines to treat them as black boxes, making AISQL queries difficult to optimize. In this paper, we introduce Larch, a framework for optimizing the execution of semantic filters in AI SQL queries. Larch was inspired by two key observations: i) the high latency of semantic operators leaves significant room for computationally-heavy runtime optimization techniques, ii) unstructured data are typically accompanied by semantic information in the form of embeddings allowing for efficient semantic comparisons between AI_FILTER prompts and data values. Based on these two key observations, we present two Larch variants: Larch-A2C and Larch-Sel. Larch-A2C encodes arbitrary semantic filters expression tree using an embedding-augmented Gated Graph Neural Network and formulates the filter evaluation order as a Markov decision process. In contrast, Larch-Sel leverages a supervised learning model to predict filter selectivities, subsequently applying dynamic programming to find a near-optimal evaluation order for each input row. Evaluated across diverse real-world datasets and comprehensive synthetic workloads, both Larch variants always outperform existing semantic filter optimization techniques in terms of token usage. Our results demonstrate that Larch is robust across diverse workloads, reducing total token cost overhead by 3x-19x compared to Palimpzest and Quest.

Related papers

• SemJoin: Semantic Join Optimization [5.770286315818393]
  A semantic join can be evaluated with a large language model (LLM), but comparing every pair of predicates requires O(M x N) invocations and is cost-prohibitive at scale.<n>We propose an LLM-agent-based decision pipeline that optimize semantic joins by matching the execution strategy of the underlying tables.
  arXiv  Detail & Related papers  (2026-06-28T17:57:10Z)
• ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering [55.55968342644846]
  Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering.<n>Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility.<n>We propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR.<n> Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-04-10T06:09:41Z)
• Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm [17.52767415071768]
  Clustering-Sampling-Voting (CSV) is a framework that reduces invocations to sublinear complexity while providing error guarantees.<n>CSV embeds semantic clusters into semantic clusters, samples a small subset for evaluation, and infers cluster-level labels via two proposed voting strategies.
  arXiv  Detail & Related papers  (2026-03-05T04:37:15Z)
• Filtered Approximate Nearest Neighbor Search in Vector Databases: System Design and Performance Analysis [0.5249805590164902]
  Filtered Approximate Nearest Neighbor Search (FANNS) is used to combine semantic retrieval with metadata constraints.<n>In this work, we systematize the taxonomy of filtering strategies and evaluate their integration into vectors.<n>Our experiments reveal that algorithmic adaptations within the engine often override raw index performance.
  arXiv  Detail & Related papers  (2026-02-11T23:40:26Z)
• LLM-based Semantic Search for Conversational Queries in E-commerce [1.3645712130536118]
  We present an LLM-based semantic search framework that captures user intent from conversational queries.<n>Our framework achieves strong precision and recall across various settings compared to baseline approaches on a real-world dataset.
  arXiv  Detail & Related papers  (2026-01-23T06:35:28Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study [8.482898222291206]
  Triple (subject-relationobject) extraction from text is the fundamental building block of KG construction.<n>Recent work in NLP tasks (e.g. autonomy generation) uses automatic prompt optimization/engineering to address this challenge.<n>We evaluate different settings by changing (a) the prompting strategy, (b) the LLM being used for prompt optimization and task execution, (c) the number of canonical relations in the schema, (d) the length and diversity of input text, (e) the metric used to drive the prompt optimization, and (f) the dataset being used for training and testing.
  arXiv  Detail & Related papers  (2025-06-24T16:38:49Z)
• Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs [51.33342412699939]
  Knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. Recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. We propose an effective Query Instruction Parsing (QIPP) that captures latent query patterns from code-like query instructions.
  arXiv  Detail & Related papers  (2024-10-27T03:18:52Z)
• 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)
• Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding [84.04706075621013]
  We present a general-purpose, modular neural semantic parsing framework based on token-level fine-grained query understanding. Our framework consists of three modules: named entity recognizer (NER), neural entity linker (NEL) and neural entity linker (NSP)
  arXiv  Detail & Related papers  (2022-09-28T21:00:30Z)
• Deep Graph Matching and Searching for Semantic Code Retrieval [76.51445515611469]
  We propose an end-to-end deep graph matching and searching model based on graph neural networks. We first represent both natural language query texts and programming language code snippets with the unified graph-structured data. In particular, DGMS not only captures more structural information for individual query texts or code snippets but also learns the fine-grained similarity between them.
  arXiv  Detail & Related papers  (2020-10-24T14:16:50Z)

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.