mlsanityData to 14 Oct 2026

Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA

arXiv 2509.01158 ↗First posted 1 Sep 2025cs.CLcited by 0

On the map: Mixture-of-experts → Mixture of LoRA experts

Abstract (arXiv)

Chinese information extraction (IE) involves multiple tasks across diverse temporal domains, including Classical and Modern documents. Fine-tuning a single model on heterogeneous tasks and across different eras may lead to interference and reduced performance. Therefore, in this paper, we propose Tea-MOELoRA, a parameter-efficient multi-task framework that combines LoRA with a Mixture-of-Experts (MoE) design. Multiple low-rank LoRA experts specialize in different IE tasks and eras, while a task-era-aware router mechanism dynamically allocates expert contributions. Experiments show that Tea-MOELoRA outperforms both single-task and joint LoRA baselines, demonstrating its ability to leverage task and temporal knowledge effectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Mixture of LoRA experts, one of 12 directions in Mixture-of-experts. Builds on 10 of its 25 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

10 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025CoLA: Collaborative Low-Rank Adaptation21 May

Other references · 9

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Compositioncited by 364
  3. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  4. 2024HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuningcited by 123
  5. 2023When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applicationscited by 111
  6. 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
  7. 2024TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competitioncited by 10
  8. 2024CHisIEC: An Information Extraction Corpus for Ancient Chinese Historycited by 7
  9. 2022That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memorycited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
  2. 2025Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning
  3. 2024RUIE: Retrieval-based Unified Information Extraction using Large Language Model
  4. 2024Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction
  5. 2025From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning
  6. 2026Task-Aware LoRA Adapter Composition via Similarity Retrieval in Vector Databases
  7. 2023Task-Based MoE for Multitask Multilingual Machine Translation
  8. 2025Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning