mlsanityData to 14 Oct 2026

Retrieval Augmentation for Commonsense Reasoning: A Unified Approach

arXiv 2210.12887 ↗First posted 23 Oct 2022cs.CL cs.AIcited by 14

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such methods to commonsense reasoning tasks faces two unique challenges, i.e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever. In this paper, we systematically investigate how to leverage commonsense knowledge retrieval to improve commonsense reasoning tasks. We proposed a unified framework of retrieval-augmented commonsense reasoning (called RACo), including a newly constructed commonsense corpus with over 20 million documents and novel strategies for training a commonsense retriever. We conducted experiments on four different commonsense reasoning tasks. Extensive evaluation results showed that our proposed RACo can significantly outperform other knowledge-enhanced method counterparts, achieving new SoTA performance on the CommonGen and CREAK leaderboards.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 50 of its 70 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

50 of 70 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answering21 Jan

Other references · 49

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  9. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  10. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  11. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
37 more
  1. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  2. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  3. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  5. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  6. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  8. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 824
  9. 2017Dense-Captioning Events in Videoscited by 793
  10. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  11. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  12. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  13. 2019VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Researchcited by 414
  14. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  15. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  16. 2019Abductive Commonsense Reasoningcited by 301
  17. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
  18. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 252
  19. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  20. 2022A Survey on Retrieval-Augmented Text Generationcited by 158
  21. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  22. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 109
  23. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  24. 2021UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmarkcited by 98
  25. 2021CREAK: A Dataset for Commonsense Reasoning over Entity Knowledgecited by 88
  26. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
  27. 2019Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphscited by 59
  28. 2020Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graphcited by 57
  29. 2020GenericsKB: A Knowledge Base of Generic Statementscited by 51
  30. 2020SemEval-2020 Task 4: Commonsense Validation and Explanationcited by 42
  31. 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
  32. 2022AdaPrompt: Adaptive Model Training for Prompt-based NLPcited by 30
  33. 2020Differentiable Open-Ended Commonsense Reasoningcited by 29
  34. 2022Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Expertscited by 19
  35. 2021Retrieval Enhanced Model for Commonsense Generationcited by 18
  36. 2021Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrievalcited by 8
  37. 2021Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answeringcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 4; 2025: 3; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  2. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 98
  3. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  4. 2024An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaborationcited by 16
  5. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  6. 2024Stepwise Self-Consistent Mathematical Reasoning with Large Language Modelscited by 8
  7. 2023Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verificationcited by 4
  8. 2023SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoningcited by 3
  9. 2023Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrievalcited by 1
  10. 2025Estimating Commonsense Plausibility through Semantic Shiftscited by 1
  11. 2022Very Large Language Model as a Unified Methodology of Text Miningcited by 0
  12. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generationcited by 0
2 more
  1. 2025DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QAcited by 0
  2. 2026The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey of Reasoning-Intensive Retrieval: Progress and Challenges
  2. 2024ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering
  3. 2025CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge
  4. 2022CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
  5. 2026CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models
  6. 2025RaDeR: Reasoning-aware Dense Retrieval Models
  7. 2023Retrieval-Generation Synergy Augmented Large Language Models
  8. 2025Towards Quantifying Commonsense Reasoning with Mechanistic Insights