Large Language Models for Continual Relation Extraction
Preprint
- 6 January 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Real-world data streams, such as news articles and social media posts, are dynamic and nonstationary, creating challenges for real-time structured representation via knowledge graphs, where relation extraction is a key component. Continual relation extraction (CRE) addresses this setting by incrementally learning new relations while preserving previously acquired knowledge. This work investigates the use of pretrained language models for CRE, focusing on large language models (LLMs) and the effectiveness of memory replay in mitigating forgetting. We evaluated decoder-only models and an encoder-decoder model on TACRED and FewRel in English. Our results show that memory replay is most beneficial for smaller instruction-tuned models (e.g., Flan-T5 Base) and base models such as Llama2-7B-hf. In contrast, the remaining instruction-tuned models in this work do not benefit from memory replay, yet some, like Mistral-7B, already achieve higher accuracies without it and surpass prior methods. We further observed that Llama models in this work are more prone to hallucinations. To the best of our knowledge, this work provides the first reproducible benchmarks for LLMs in CRE. It offers a novel analysis of knowledge retention and hallucination behavior—dimensions that have not been systematically studied in earlier research.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Continual learning and catastrophic forgetting2024
- Knowledge Graphs, Large Language Models, and Hallucinations: An NLP PerspectiveJournal of Web Semantics, 2024
- Continual Few-Shot Relation Extraction with Prompt-Based Contrastive Learning2024
- Improving Continual Relation Extraction with LSTM and Back Forward Projection2023
- Class Incremental Learning with Important and Diverse Memory2023
- From learned to new relations through generative models combined with relations clustering and few-shot learning2023
- Relational Representation Learning for Zero-Shot Relation Extraction with Instance Prompting and Prototype Rectification2023
- Continual relation extraction via linear mode connectivity and interval cross trainingKnowledge-Based Systems, 2023
- Pre-Trained Language Models and Their ApplicationsEngineering, 2022
- Efficient Lifelong Relation Extraction with Dynamic Regularization2020