mlsanityData to 14 Oct 2026

Retrieval Enhanced Model for Commonsense Generation

arXiv 2105.11174 ↗First posted 24 May 2021cs.CL cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even puzzles strong pre-trained language generation models. We propose a novel framework using retrieval methods to enhance both the pre-training and fine-tuning for commonsense generation. We retrieve prototype sentence candidates by concept matching and use them as auxiliary input. For fine-tuning, we further boost its performance with a trainable sentence retriever. We demonstrate experimentally on the large-scale CommonGen benchmark that our approach achieves new state-of-the-art results.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 24 May 2021.

Builds on

19 of 29 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  5. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  6. 2019Language Models as Knowledge Bases?cited by 1,936
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  8. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  10. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 824
  11. 2017Dense-Captioning Events in Videoscited by 793
  12. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 670
7 more
  1. 2019VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Researchcited by 414
  2. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  3. 2020UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Trainingcited by 204
  4. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  5. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  6. 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
  7. 2020An Enhanced Knowledge Injection Model for Commonsense Generationcited by 21

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 9; 2023: 1; 2024: 2; 2025: 2.

18 papers.

Sort:

By area:

  1. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  2. 2025Retrieval-Augmented Generation with Conflicting Evidencecited by 63
  3. 2024RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Recordscited by 21
  4. 2022Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarizationcited by 14
  5. 2022Retrieval Augmentation for Commonsense Reasoning: A Unified Approachcited by 14
  6. 2021Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Modelscited by 9
  7. 2021SAPPHIRE: Approaches for Enhanced Concept-to-Text Generationcited by 8
  8. 2022Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoningcited by 8
  9. 2023Expository Text Generation: Imitate, Retrieve, Paraphrasecited by 8
  10. 2021Contextualized Scene Imagination for Generative Commonsense Reasoningcited by 7
  11. 2021KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generationcited by 6
  12. 2022Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approachcited by 4
6 more
  1. 2022CoSe-Co: Text Conditioned Generative CommonSense Contextualizercited by 3
  2. 2022VER: Unifying Verbalizing Entities and Relationscited by 2
  3. 2022Lexical Complexity Controlled Sentence Generationcited by 2
  4. 2022ConceptNet infused DialoGPT for Underlying Commonsense Understanding and Reasoning in Dialogue Response Generationcited by 1
  5. 2024LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAGcited by 1
  6. 2025Do LLMs exhibit the same commonsense capabilities across languages?cited by 1