Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908892211970048 |
|---|---|
| author | Tu, Mingchen Liu, Zhiqiang Li, Juan Liu, Liangyurui Wang, Junjie Liang, Lei Zhang, Wen |
| author_facet | Tu, Mingchen Liu, Zhiqiang Li, Juan Liu, Liangyurui Wang, Junjie Liang, Lei Zhang, Wen |
| contents | Although Large Language Models (LLMs) perform exceptionally well in general domains, the problem of hallucinations poses significant risks in specialized fields such as healthcare and law, where high interpretability is essential. Existing fine-tuning methods depend heavily on large-scale professional datasets, which are often hard to obtain due to the privacy regulations. Moreover, existing self-evolution methods are primarily designed for general domains, which may struggle to adapt to knowledge-intensive domains due to the lack of knowledge constraints. In this paper, we propose an ontology rule guided method Evontree to enable self-evolution of LLMs in low-resource specialized domains. Specifically, Evontree first extracts domain ontology knowledge from raw models, then detects knowledge inconsistencies using two core ontology rules, and finally reinforces gap knowledge into model via self-distilled fine-tuning. Extensive evaluations on medical QA benchmarks using Llama3-8B-Instruct and Med42-V2 demonstrate the effectiveness of Evontree, which outperforms both the base models and strong baselines, achieving up to a 3.7\% improvement in accuracy. Detailed ablation studies further validate the robustness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26683 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models Tu, Mingchen Liu, Zhiqiang Li, Juan Liu, Liangyurui Wang, Junjie Liang, Lei Zhang, Wen Computation and Language Artificial Intelligence Although Large Language Models (LLMs) perform exceptionally well in general domains, the problem of hallucinations poses significant risks in specialized fields such as healthcare and law, where high interpretability is essential. Existing fine-tuning methods depend heavily on large-scale professional datasets, which are often hard to obtain due to the privacy regulations. Moreover, existing self-evolution methods are primarily designed for general domains, which may struggle to adapt to knowledge-intensive domains due to the lack of knowledge constraints. In this paper, we propose an ontology rule guided method Evontree to enable self-evolution of LLMs in low-resource specialized domains. Specifically, Evontree first extracts domain ontology knowledge from raw models, then detects knowledge inconsistencies using two core ontology rules, and finally reinforces gap knowledge into model via self-distilled fine-tuning. Extensive evaluations on medical QA benchmarks using Llama3-8B-Instruct and Med42-V2 demonstrate the effectiveness of Evontree, which outperforms both the base models and strong baselines, achieving up to a 3.7\% improvement in accuracy. Detailed ablation studies further validate the robustness of our approach. |
| title | Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.26683 |