mlsanityData to 13 Oct 2026

Rationale-Enhanced Language Models are Better Continual Relation Learners

arXiv 2310.06547 ↗First posted 10 Oct 2023cs.CL cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 13 papers in the map (data through 13 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

16 of 21 references.

References · 16

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  4. 2017Gradient Episodic Memory for Continual Learningcited by 1,882
  5. 2022Teaching Small Language Models to Reasoncited by 282
  6. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  7. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  8. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 124
  9. 2019Sentence Embedding Alignment for Lifelong Relation Extractioncited by 70
  10. 2023An Empirical Study on Information Extraction using Large Language Modelscited by 46
  11. 2022Can Rationalization Improve Robustness?cited by 36
  12. 2022Consistent Representation Learning for Continual Relation Extractioncited by 28
4 more
  1. 2022Improving Continual Relation Extraction through Prototypical Contrastive Learningcited by 14
  2. 2022Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentationcited by 13
  3. 2023Improving Continual Relation Extraction by Distinguishing Analogous Semanticscited by 9
  4. 2022Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approachcited by 8

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 7; 2025: 5; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024Continual Learning for Large Language Models: A Surveycited by 144
  2. 2024Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Modelscited by 30
  3. 2025SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMscited by 23
  4. 2024Retrieval-Augmented Generation-based Relation Extractioncited by 9
  5. 2024Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworkscited by 6
  6. 2024Boosting LLM Translation Skills without General Ability Loss via Rationale Distillationcited by 5
  7. 2025ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuningcited by 5
  8. 2024Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversationscited by 2
  9. 2024Lifelong Event Detection via Optimal Transportcited by 2
  10. 2025Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Casescited by 2
  11. 2025WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Promptingcited by 1
  12. 2026When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platformscited by 1
1 more
  1. 2025Post-Training Language Models for Continual Relation Extractioncited by 0