mlsanityData to 13 Oct 2026

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

arXiv 2106.06823 ↗First posted 12 Jun 2021cs.CL cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human performance on such tasks, while providing little human-interpretable evidence of the underlying reasoning they use. In this work, we show how to use these same models to generate such evidence: inspired by the contrastive nature of human explanations, we use PLMs to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer (for example, peanuts are usually salty while raisins are sweet). Conditioning model decisions on these explanations improves performance on two commonsense reasoning benchmarks, as compared to previous non-contrastive alternatives. These explanations are also judged by humans to be more relevant for solving the task, and facilitate a novel method to evaluate explanation faithfulfness.

Key facts. Cited by 45 papers in the map (data through 13 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 12 Jun 2021.

Builds on

36 of 49 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,884
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,893
  5. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,843
  6. 2019Language Models as Knowledge Bases?cited by 1,931
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,805
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,725
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,203
  10. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 717
  11. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 526
  12. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
24 more
  1. 2018Gender Bias in Coreference Resolutioncited by 439
  2. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 433
  3. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  4. 2018Hypothesis Only Baselines in Natural Language Inferencecited by 294
  5. 2016Rationalizing Neural Predictionscited by 281
  6. 2018A Simple Method for Commonsense Reasoningcited by 223
  7. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 201
  8. 2020How Context Affects Language Models' Factual Predictionscited by 181
  9. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 173
  10. 2019oLMpics -- On what Language Model Pre-training Capturescited by 161
  11. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  12. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
  13. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  14. 2020Enabling Language Models to Fill in the Blankscited by 121
  15. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 105
  16. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  17. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  18. 2018Contrastive Explanation: A Structural-Model Approachcited by 64
  19. 2020Generative Data Augmentation for Commonsense Reasoningcited by 49
  20. 2020WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challengecited by 43
  21. 2019Can I Trust the Explainer? Verifying Post-hoc Explanatory Methodscited by 37
  22. 2020Explaining Question Answering Models through Text Generationcited by 33
  23. 2020Self-supervised Knowledge Triplet Learning for Zero-shot Question Answeringcited by 29
  24. 2019What Does My QA Model Know? Devising Controlled Probes using Expert Knowledgecited by 19

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 2; 2022: 14; 2023: 17; 2024: 7; 2025: 4; 2026: 1.

45 papers.

Sort:

By area:

  1. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  2. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  3. 2022A Review on Language Models as Knowledge Basescited by 156
  4. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  5. 2023Reasoning Implicit Sentiment with Chain-of-Thought Promptingcited by 79
  6. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  7. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 52
  8. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  9. 2023Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationalescited by 37
  10. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  11. 2022CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generationcited by 23
  12. 2025Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Thinkcited by 16
33 more
  1. 2023Crystal: Introspective Reasoners Reinforced with Self-Feedbackcited by 15
  2. 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignmentcited by 14
  3. 2022Investigating the Benefits of Free-Form Rationalescited by 13
  4. 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methodscited by 13
  5. 2023Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanationscited by 13
  6. 2023A Systematic Survey of Prompt Engineering on Vision-Language Foundation Modelscited by 12
  7. 2023Large Language Model Programscited by 11
  8. 2023Rather a Nurse than a Physician -- Contrastive Explanations under Investigationcited by 11
  9. 2023Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecturecited by 10
  10. 2023FLamE: Few-shot Learning from Natural Language Explanationscited by 10
  11. 2024Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledgecited by 10
  12. 2022Elaboration-Generating Commonsense Question Answering at Scalecited by 9
  13. 2022Does Self-Rationalization Improve Robustness to Spurious Correlations?cited by 9
  14. 2024A Survey on Symbolic Knowledge Distillation of Large Language Modelscited by 9
  15. 2022Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Inductioncited by 8
  16. 2023Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differencescited by 8
  17. 2023Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answeringcited by 6
  18. 2022Unsupervised Explanation Generation via Correct Instantiationscited by 5
  19. 2022An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphscited by 4
  20. 2023Knowledge-enhanced Neural Machine Reasoning: A Reviewcited by 3
  21. 2023UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilitiescited by 3
  22. 2025Towards Multimodal Metaphor Understanding: A Chinese Dataset and Model for Metaphor Mapping Identificationcited by 3
  23. 2022Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI)cited by 2
  24. 2022CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classificationcited by 2
  25. 2024Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?cited by 1
  26. 2024Abdelhak at SemEval-2024 Task 9 : Decoding Brainteasers, The Efficacy of Dedicated Models Versus ChatGPTcited by 1
  27. 2025Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibilitycited by 1
  28. 2023UFO: Unified Fact Obtaining for Commonsense Question Answeringcited by 0
  29. 2023Open-ended Commonsense Reasoning with Unrestricted Answer Scopecited by 0
  30. 2023Contrastive Learning for Inference in Dialoguecited by 0
  31. 2024Persona Knowledge-Aligned Prompt Tuning Method for Online Debatecited by 0
  32. 2025Incongruence Identification in Eyewitness Testimonycited by 0
  33. 2026Contextual Discrepancy-Aware Contrastive Learning for Robust Medical Time Series Diagnosis in Small-Sample Scenarioscited by 0