mlsanityData to 7 Oct 2026

End-to-End Trainable Retrieval-Augmented Generation for Relation Extraction

arXiv 2406.03790 ↗First posted 6 Jun 2024cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

This paper addresses a crucial challenge in retrieval-augmented generation-based relation extractors; the end-to-end training is not applicable to conventional retrieval-augmented generation due to the non-differentiable nature of instance retrieval. This problem prevents the instance retrievers from being optimized for the relation extraction task, and conventionally it must be trained with an objective different from that for relation extraction. To address this issue, we propose a novel End-to-end Trainable Retrieval-Augmented Generation (ETRAG), which allows end-to-end optimization of the entire model, including the retriever, for the relation extraction objective by utilizing a differentiable selection of the k nearest instances. We evaluate the relation extraction performance of ETRAG on the TACRED dataset, which is a standard benchmark for relation extraction. ETRAG demonstrates consistent improvements against the baseline model as retrieved instances are added. Furthermore, the analysis of instances retrieved by the end-to-end trained retriever confirms that the retrieved instances contain common relation labels or entities with the query and are specialized for the target task. Our findings provide a promising foundation for future research on retrieval-augmented generation and the broader applications of text generation in Natural Language Processing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 58 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

32 of 58 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  8. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  11. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  12. 2018Deep contextualized word representationscited by 2,285
20 more
  1. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  2. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  3. 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
  4. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  5. 2023Revisiting Relation Extraction in the era of Large Language Modelscited by 100
  6. 2018Neural Nearest Neighbors Networkscited by 98
  7. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  8. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  9. 2023Graph Neural Prompting with Large Language Modelscited by 64
  10. 2023GPT-RE: In-context Learning for Relation Extraction using Large Language Modelscited by 62
  11. 2019Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Networkcited by 51
  12. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  13. 2018Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extractioncited by 42
  14. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
  15. 2023DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extractioncited by 37
  16. 2022Summarization as Indirect Supervision for Relation Extractioncited by 31
  17. 2022Unified Semantic Typing with Meaningful Label Inferencecited by 18
  18. 2022Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extractioncited by 7
  19. 2021Instance-Based Neural Dependency Parsingcited by 3
  20. 2023Descriptive Knowledge Graph in Biomedical Domaincited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval-Augmented Generation-based Relation Extraction
  2. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
  3. 2024Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
  4. 2025SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
  5. 2024Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks
  6. 2025ImpRAG: Retrieval-Augmented Generation with Implicit Queries
  7. 2025GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
  8. 2026ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models