# Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties

arXiv: https://arxiv.org/abs/2511.03407 · HTML: https://mlsanity.com/paper/2511.03407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 5 Nov 2025.

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

- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws](https://mlsanity.com/paper/2404.05405/) (2024)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [GenIE: Generative Information Extraction](https://mlsanity.com/paper/2112.08340/) (2021)
- [Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning](https://mlsanity.com/paper/2304.02711/) (2023)
- [Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text](https://mlsanity.com/paper/2308.02357/) (2023)
- [Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://mlsanity.com/paper/2403.02990/) (2024)
- [Importance Weighting Can Help Large Language Models Self-Improve](https://mlsanity.com/paper/2408.09849/) (2024)
- [Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study](https://mlsanity.com/paper/2210.10678/) (2022)
- [Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE](https://mlsanity.com/paper/2505.12533/) (2025)

## Abstract (arXiv)

Small language models (SLMs) have shown promises for relation extraction (RE) when extracting RDF triples guided by SHACL shapes focused on common datatype properties. This paper investigates how SLMs handle both datatype and object properties for a complete RDF graph extraction. We show that the key bottleneck is related to long-tail distribution of rare properties. To solve this issue, we evaluate several strategies: stratified sampling, weighted loss, dataset scaling, and template-based synthetic data augmentation. We show that the best strategy to perform equally well over unbalanced target properties is to build a training set where the number of occurrences of each property exceeds a given threshold. To enable reproducibility, we publicly released our datasets, experimental results and code. Our findings offer practical guidance for training shape-aware SLMs and highlight promising directions for future work in semantic RE.