# Kastor: Fine-tuned Small Language Models for Shape-based Active Relation Extraction

arXiv: https://arxiv.org/abs/2511.03466 · HTML: https://mlsanity.com/paper/2511.03466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness](https://mlsanity.com/paper/2411.03350/) (2024)
- [Small Language Models: Survey, Measurements, and Insights](https://mlsanity.com/paper/2409.15790/) (2024)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation](https://mlsanity.com/paper/2310.15638/) (2023)
- [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://mlsanity.com/paper/2311.08526/) (2023)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [GenIE: Generative Information Extraction](https://mlsanity.com/paper/2112.08340/) (2021)
- [DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction](https://mlsanity.com/paper/2302.08675/) (2023)
- [A Study of the Quality of Wikidata](https://mlsanity.com/paper/2107.00156/) (2021)
- [Annotator-Centric Active Learning for Subjective NLP Tasks](https://mlsanity.com/paper/2404.15720/) (2024)
- [KnowGL: Knowledge Generation and Linking from Text](https://mlsanity.com/paper/2210.13952/) (2022)
- [Construction of Knowledge Graphs: State and Challenges](https://mlsanity.com/paper/2302.11509/) (2023)
- [Retrieval-Augmented Generation-based Relation Extraction](https://mlsanity.com/paper/2404.13397/) (2024)
- [The Effects of Hallucinations in Synthetic Training Data for Relation Extraction](https://mlsanity.com/paper/2410.08393/) (2024)
- [REDrm FM: a Filtered and Multilingual Relation Extraction Dataset](https://mlsanity.com/paper/2306.09802/) (2023)
- [Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction](https://mlsanity.com/paper/2404.17809/) (2024)
- [Need a Small Specialized Language Model? Plan Early!](https://mlsanity.com/paper/2402.01093/) (2024)

## Abstract (arXiv)

RDF pattern-based extraction is a compelling approach for fine-tuning small language models (SLMs) by focusing a relation extraction task on a specified SHACL shape. This technique enables the development of efficient models trained on limited text and RDF data. In this article, we introduce Kastor, a framework that advances this approach to meet the demands for completing and refining knowledge bases in specialized domains. Kastor reformulates the traditional validation task, shifting from single SHACL shape validation to evaluating all possible combinations of properties derived from the shape. By selecting the optimal combination for each training example, the framework significantly enhances model generalization and performance. Additionally, Kastor employs an iterative learning process to refine noisy knowledge bases, enabling the creation of robust models capable of uncovering new, relevant facts