# Prompting Contrastive Explanations for Commonsense Reasoning Tasks

arXiv: https://arxiv.org/abs/2106.06823 · HTML: https://mlsanity.com/paper/2106.06823/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 12 Jun 2021.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Enabling Language Models to Fill in the Blanks](https://mlsanity.com/paper/2005.05339/) (2020)
- [Explaining NLP Models via Minimal Contrastive Editing (MiCE)](https://mlsanity.com/paper/2012.13985/) (2020)
- [Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations](https://mlsanity.com/paper/1910.03065/) (2019)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)

## Built on by (most cited first, 30 of 45)

- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [Iteratively Prompt Pre-trained Language Models for Chain of Thought](https://mlsanity.com/paper/2203.08383/) (2022)
- [Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness](https://mlsanity.com/paper/2301.08881/) (2023)
- [Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering](https://mlsanity.com/paper/2210.03078/) (2022)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [Heterogeneous Contrastive Learning for Foundation Models and Beyond](https://mlsanity.com/paper/2404.00225/) (2024)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think](https://mlsanity.com/paper/2504.20708/) (2025)
- [Crystal: Introspective Reasoners Reinforced with Self-Feedback](https://mlsanity.com/paper/2310.04921/) (2023)
- [AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment](https://mlsanity.com/paper/2407.01965/) (2024)
- [Investigating the Benefits of Free-Form Rationales](https://mlsanity.com/paper/2206.11083/) (2022)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)
- [Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations](https://mlsanity.com/paper/2305.03117/) (2023)
- [A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models](https://mlsanity.com/paper/2307.12980/) (2023)
- [Large Language Model Programs](https://mlsanity.com/paper/2305.05364/) (2023)
- [Rather a Nurse than a Physician -- Contrastive Explanations under Investigation](https://mlsanity.com/paper/2310.11906/) (2023)
- [Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture](https://mlsanity.com/paper/2305.12710/) (2023)
- [FLamE: Few-shot Learning from Natural Language Explanations](https://mlsanity.com/paper/2306.08042/) (2023)
- [Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge](https://mlsanity.com/paper/2402.14310/) (2024)
- [Elaboration-Generating Commonsense Question Answering at Scale](https://mlsanity.com/paper/2209.01232/) (2022)
- [Does Self-Rationalization Improve Robustness to Spurious Correlations?](https://mlsanity.com/paper/2210.13575/) (2022)
- [A Survey on Symbolic Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2408.10210/) (2024)
- [Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction](https://mlsanity.com/paper/2202.04876/) (2022)
- [Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences](https://mlsanity.com/paper/2312.01582/) (2023)
- [Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2305.08135/) (2023)
- [Unsupervised Explanation Generation via Correct Instantiations](https://mlsanity.com/paper/2211.11160/) (2022)

## 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.