# Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing

arXiv: https://arxiv.org/abs/2610.08095 · HTML: https://mlsanity.com/paper/2610.08095/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 4 of 4)

- [Research Trends for the Interplay between Large Language Models and Knowledge Graphs](https://mlsanity.com/paper/2406.08223/) (2024)
- [SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection](https://mlsanity.com/paper/2507.13859/) (2025)
- [Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval](https://mlsanity.com/paper/2502.13369/) (2025)
- [SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions](https://mlsanity.com/paper/2512.14277/) (2025)

## Abstract (arXiv)

Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data model. QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations. An offline distiller produces TTQL, a compact description of populated multi-hop patterns, conditional frequencies and path-conditioned literal examples, plus a class-property co-occurrence matrix. Online, TTQL guides the LLM, while deterministic syntax, vocabulary and data-model checks provide diagnostics for iterative refinement. On CK25 (First International Text2SPARQL Challenge), under matched-condition recomputation on a QLever snapshot, QRAKEN achieves strict F1 of 0.643 ± 0.026 with GPT-4.1 mini and 0.652 ± 0.012 with GPT-5.4: relative gains of 30% and 32% over the strongest recomputed participant, outperforming systems using the same base model family. Ablations identify TTQL patterns as the dominant driver (+0.31 strict F1 over a shape-only baseline); the refinement loop provides a cheap safety net, rejecting triple patterns unsupported by the co-occurrence matrix. Compared with auto-derived SHACL, TTQL yields 64% higher strict F1, supporting the value of empirical patterns beyond schema exposure. With two local 35B 4-bit open-weight models at zero marginal cost, the same pipeline matches the strongest recomputed participant, and TTQL advantages over shape-only and SHACL baselines persist. Results on a single, relatively small benchmark provide an initial empirical signal; monolithic TTQL injection on very open cross-domain graphs remains the main limitation.