mlsanityData to 7 Oct 2026

Elaboration-Generating Commonsense Question Answering at Scale

arXiv 2209.01232 ↗First posted 2 Sep 2022cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models -- an elaboration generator and an answer predictor -- allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap on GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

42 of 54 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2019Language Models as Knowledge Bases?cited by 1,922
  11. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  12. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
30 more
  1. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  2. 2019How Can We Know What Language Models Know?cited by 953
  3. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  4. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  5. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  6. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  7. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  8. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  9. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  10. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 248
  11. 2018A Simple Method for Commonsense Reasoningcited by 223
  12. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  13. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  14. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 194
  15. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  16. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 117
  17. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 108
  18. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  19. 2019Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answeringcited by 68
  20. 2019Zero-shot Text Classification With Generative Language Modelscited by 55
  21. 2018Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledgecited by 48
  22. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  23. 2019Improving Question Answering over Incomplete KBs with Knowledge-Aware Readercited by 37
  24. 2019Careful Selection of Knowledge to solve Open Book Question Answeringcited by 35
  25. 2020Explaining Question Answering Models through Text Generationcited by 33
  26. 2018Reasoning about Actions and State Changes by Injecting Commonsense Knowledgecited by 29
  27. 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
  28. 2021Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformationcited by 19
  29. 2020Contextualized Representations Using Textual Encyclopedic Knowledgecited by 17
  30. 2022Clues Before Answers: Generation-Enhanced Multiple-Choice QAcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 1.

9 papers.

  1. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  2. 2022Self-Prompting Large Language Models for Zero-Shot Open-Domain QAcited by 39
  3. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  4. 2023Crystal: Introspective Reasoners Reinforced with Self-Feedbackcited by 15
  5. 2023FLamE: Few-shot Learning from Natural Language Explanationscited by 10
  6. 2024Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Promptingcited by 10
  7. 2024DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questionscited by 7
  8. 2025Robust Misinformation Detection by Visiting Potential Commonsense Conflictcited by 3
  9. 2024Rehearsing Answers to Probable Questions with Perspective-Takingcited by 0