OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

• URL: http://arxiv.org/abs/2605.29250v1
• Date: Thu, 28 May 2026 02:10:35 GMT
• Title: OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
• Abstract summary: Existing retrievers operate over one source at a time under a fixed query language.<n>We present OmniRetrieval, a framework that takes any natural-language query and identifies appropriate knowledge sources.
• Score: 67.62754856088591
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces. A natural attempt at unification would collapse these sources into a shared space, but this erases the structural affordances (such as schemas, ontologies, compositional operators) that give each source its expressive power. Effective retrieval over diverse knowledge, therefore, requires not homogenization but an overarching layer that meets each source on its own terms. To achieve this, we present OmniRetrieval, a framework that takes any natural-language query, identifies appropriate knowledge sources, and dispatches source-native queries to their native execution engines. Across an extensive benchmark spanning 13 datasets and 309 distinct knowledge bases over text, relational, and graph-structured sources, OmniRetrieval exceeds single-source baselines, demonstrating that it can serve as a general-purpose interface to the heterogeneous sources while preserving the structural distinctions that make each source valuable.

Related papers

• On the Power of Source Screening for Learning Shared Feature Extractors [33.10812756558517]
  It is well understood that data sources with low relevance or poor quality may hinder representation learning.<n>We focus on the question of which data sources should be learned jointly by focusing on the traditionally deemed good'' collection of sources.<n>We find that source screening can play a central role in statistically optimal subspace estimation.
  arXiv  Detail & Related papers  (2026-02-18T01:32:10Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue [72.26474540602517]
  SAFARI is a novel framework for planning, understanding, and incorporating under both supervised and unsupervised settings. We construct a personalized knowledge-grounded dialogue dataset textittextbfKnowledge textbfBehind textbfPersona(textbfKBP) Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.
  arXiv  Detail & Related papers  (2023-10-13T03:38:38Z)
• Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources [87.26486246513063]
  Chain-of-knowledge (CoK) is a framework that augments large language models. CoK consists of three stages: reasoning preparation, dynamic knowledge adapting, and answer consolidation.
  arXiv  Detail & Related papers  (2023-05-22T17:34:23Z)
• Learning To Rank Resources with GNN [7.337247167823921]
  We propose a graph neural network (GNN) based approach to learning-to-rank that is capable of modeling resource-query and resource-resource relationships. Our method outperforms the state-of-the-art by 6.4% to 42% on various performance metrics.
  arXiv  Detail & Related papers  (2023-04-17T02:01:45Z)
• Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation [63.24594955429465]
  Multi-source entity linkage is critical in high-impact applications such as data cleaning and user stitching. AdaMEL is a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage. Our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning.
  arXiv  Detail & Related papers  (2021-10-27T15:20:41Z)
• Dimensions of Commonsense Knowledge [60.49243784752026]
  We survey a wide range of popular commonsense sources with a special focus on their relations. We consolidate these relations into 13 knowledge dimensions, each abstracting over more specific relations found in sources.
  arXiv  Detail & Related papers  (2021-01-12T17:52:39Z)
• Unified Open-Domain Question Answering with Structured and Unstructured Knowledge [7.7429684536437104]
  We study open-domain question answering (ODQA) with structured, unstructured and semi-structured knowledge sources. Our approach homogenizes all sources by reducing them to text, and applies recent, powerful retriever-reader models. As a result, our unified model produces state-of-the-art results on 3 popular ODQA benchmarks.
  arXiv  Detail & Related papers  (2020-12-29T05:14:08Z)

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.