Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.15098 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917224347860992 |
|---|---|
| author | Zhou, Chenyue Solmaz, Gürkan Cirillo, Flavio Gashteovski, Kiril Fürst, Jonathan |
| author_facet | Zhou, Chenyue Solmaz, Gürkan Cirillo, Flavio Gashteovski, Kiril Fürst, Jonathan |
| contents | Humanitarian Mine Action (HMA) addresses the challenge of detecting and removing landmines from conflict regions. Much of the life-saving operational knowledge produced by HMA agencies is buried in unstructured reports, limiting the transferability of information between agencies. To address this issue, we propose TextMineX: the first dataset, evaluation framework and ontology-guided large language model (LLM) pipeline for knowledge extraction from text in the HMA domain. TextMineX structures HMA reports into (subject, relation, object)-triples, thus creating domain-specific knowledge. To ensure real-world relevance, we utilized the dataset from our collaborator Cambodian Mine Action Centre (CMAC). We further introduce a bias-aware evaluation framework that combines human-annotated triples with an LLM-as-Judge protocol to mitigate position bias in reference-free scoring. Our experiments show that ontology-aligned prompts improve extraction accuracy by up to 44.2%, reduce hallucinations by 22.5%, and enhance format adherence by 20.9% compared to baseline models. We publicly release the dataset and code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15098 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TextMineX: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action Zhou, Chenyue Solmaz, Gürkan Cirillo, Flavio Gashteovski, Kiril Fürst, Jonathan Computation and Language Artificial Intelligence Humanitarian Mine Action (HMA) addresses the challenge of detecting and removing landmines from conflict regions. Much of the life-saving operational knowledge produced by HMA agencies is buried in unstructured reports, limiting the transferability of information between agencies. To address this issue, we propose TextMineX: the first dataset, evaluation framework and ontology-guided large language model (LLM) pipeline for knowledge extraction from text in the HMA domain. TextMineX structures HMA reports into (subject, relation, object)-triples, thus creating domain-specific knowledge. To ensure real-world relevance, we utilized the dataset from our collaborator Cambodian Mine Action Centre (CMAC). We further introduce a bias-aware evaluation framework that combines human-annotated triples with an LLM-as-Judge protocol to mitigate position bias in reference-free scoring. Our experiments show that ontology-aligned prompts improve extraction accuracy by up to 44.2%, reduce hallucinations by 22.5%, and enhance format adherence by 20.9% compared to baseline models. We publicly release the dataset and code. |
| title | TextMineX: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.15098 |