# GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons

arXiv: https://arxiv.org/abs/2604.21133 · HTML: https://mlsanity.com/paper/2604.21133/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2210.00063/) (2022)
- [ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking](https://mlsanity.com/paper/2207.04108/) (2022)
- [FIRST: Faster Improved Listwise Reranking with Single Token Decoding](https://mlsanity.com/paper/2406.15657/) (2024)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions](https://mlsanity.com/paper/2407.11417/) (2024)
- [GRASP: Generic Reasoning And SPARQL Generation across Knowledge Graphs](https://mlsanity.com/paper/2507.08107/) (2025)
- [The Wikidata Query Logs Dataset](https://mlsanity.com/paper/2602.14594/) (2026)

## Built on by (most cited first, 1 of 1)

- [Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window](https://mlsanity.com/paper/2609.14652/) (2026)

## Abstract (arXiv)

We present GRISP (Guided Recurrent IRI Selection over SPARQL Skeletons), a novel SPARQL-based question-answering method over knowledge graphs using a fine-tuned small language model (SLM). Given a natural-language question, the method uses the SLM to generate a natural-language SPARQL query skeleton, and then resolves the natural-language placeholders using a backtracking search that retrieves and re-ranks knowledge graph items under knowledge graph constraints. The SLM is jointly trained on skeleton generation and re-ranking data generated from question-query pairs. We evaluate the method on common Wikidata and Freebase benchmarks, and achieve better results than other state-of-the-art fine-tuning-based methods.