Rationale-Enhanced Language Models are Better Continual Relation Learners
This addresses the problem of forgetting in sequential learning for NLP researchers, but it is incremental as it builds on existing rationale-based methods.
The paper tackles catastrophic forgetting in continual relation extraction by incorporating rationales from large language models, achieving state-of-the-art performance on two standard benchmarks.
Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that catastrophic forgetting arises from the model's lack of robustness against future analogous relations. To address the issue, we introduce rationale, i.e., the explanations of relation classification results generated by large language models (LLM), into CRE task. Specifically, we design the multi-task rationale tuning strategy to help the model learn current relations robustly. We also conduct contrastive rationale replay to further distinguish analogous relations. Experimental results on two standard benchmarks demonstrate that our method outperforms the state-of-the-art CRE models.