DeSQ: Decomposition-based SPARQL Query Generation
Quick Take
DeSQ introduces a three-stage framework for SPARQL query generation, outperforming state-of-the-art methods on four out of five benchmarks. It decomposes complex questions into Atomic Constraints, generates structured outputs, and assembles them into complete queries, enhancing robustness and simplifying evaluation without requiring a live KB endpoint.
Key Points
- DeSQ decomposes questions into Atomic Constraints reflecting KB structure.
- Generates structured outputs mapping ACs to SPARQL Fragments with placeholders.
- Surpasses state-of-the-art methods on four out of five major benchmarks.
- Simplifies evaluation by eliminating the need for a live KB endpoint.
- Enables fine-grained error analysis for targeted improvements.
Article Content
From source RSS / original summaryarXiv:2606. 00203v1 Announce Type: new Abstract: Dominant approaches to Knowledge Base Question Answering (KBQA) fall into two categories. First is the generation of a formal query that suffers from brittleness and limited explainability, and the second is direct answer retrieval through KB exploration that is computationally costly and prone to hallucination.
To combine the strengths of both paradigms while mitigating their respective weaknesses, we introduce DeSQ (Decomposition-based SPARQL Query Generation), a KB-agnostic framework that operates in three stages. First, it decomposes complex questions into Atomic Constraints (ACs) that mirror the relational structure of the underlying KB.
Second, it generates a two-part structured output: (a) Mapping of each AC to its corresponding SPARQL Fragment, using standardized variable and URIs placeholders, and (b) URIs Grounding block describing each placeholder. Third, it assembles these fragments into a complete SPARQL query. DeSQ surpasses state-of-the-art approaches on four out of five major benchmarks and demonstrates superior robustness to lexical variation.
Beyond performance gains, our framework greatly simplifies evaluation by eliminating the need for a live KB endpoint, and its structured output enables fine-grained error analysis, allowing more targeted interventions for improvement.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.