# Think about it! Improving defeasible reasoning by first modeling the question scenario

arXiv: https://arxiv.org/abs/2110.12349 · HTML: https://mlsanity.com/paper/2110.12349/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 24 Oct 2021.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [End-to-End Open-Domain Question Answering with BERTserini](https://mlsanity.com/paper/1902.01718/) (2019)
- [Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2005.00646/) (2020)
- [WIQA: A dataset for "What if..." reasoning over procedural text](https://mlsanity.com/paper/1909.04739/) (2019)
- [Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/1909.05311/) (2019)
- [Universal Neural Machine Translation for Extremely Low Resource Languages](https://mlsanity.com/paper/1802.05368/) (2018)
- [Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/1910.14087/) (2019)
- [From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project](https://mlsanity.com/paper/1909.01958/) (2019)
- [Reasoning about Actions and State Changes by Injecting Commonsense Knowledge](https://mlsanity.com/paper/1808.10012/) (2018)
- [Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention](https://mlsanity.com/paper/1902.05715/) (2019)
- [proScript: Partially Ordered Scripts Generation via Pre-trained Language Models](https://mlsanity.com/paper/2104.08251/) (2021)
- [Graph Classification by Mixture of Diverse Experts](https://mlsanity.com/paper/2103.15622/) (2021)
- [Neural Language Modeling for Contextualized Temporal Graph Generation](https://mlsanity.com/paper/2010.10077/) (2020)
- [Could you give me a hint? Generating inference graphs for defeasible reasoning](https://mlsanity.com/paper/2105.05418/) (2021)
- [Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks](https://mlsanity.com/paper/1911.02060/) (2019)

## Built on by (most cited first, 20 of 20)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [LLMs cannot find reasoning errors, but can correct them given the error location](https://mlsanity.com/paper/2311.08516/) (2023)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation](https://mlsanity.com/paper/2305.00955/) (2023)
- [BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information](https://mlsanity.com/paper/2306.07934/) (2023)
- [ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations](https://mlsanity.com/paper/2212.10409/) (2022)
- [Query2CAD: Generating CAD models using natural language queries](https://mlsanity.com/paper/2406.00144/) (2024)
- [Teaching Language Models to Self-Improve through Interactive Demonstrations](https://mlsanity.com/paper/2310.13522/) (2023)
- [DREAM: Improving Situational QA by First Elaborating the Situation](https://mlsanity.com/paper/2112.08656/) (2021)
- [NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning](https://mlsanity.com/paper/2209.07662/) (2022)
- [What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations](https://mlsanity.com/paper/2310.15431/) (2023)
- [Coalescing Global and Local Information for Procedural Text Understanding](https://mlsanity.com/paper/2208.12848/) (2022)
- [Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events](https://mlsanity.com/paper/2412.05725/) (2024)
- [Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation](https://mlsanity.com/paper/2404.01532/) (2024)
- [What's Wrong? Refining Meeting Summaries with LLM Feedback](https://mlsanity.com/paper/2407.11919/) (2024)
- [Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism](https://mlsanity.com/paper/2310.14868/) (2023)
- [FLOWGEN: Fast and slow graph generation](https://mlsanity.com/paper/2207.07656/) (2022)
- [Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models](https://mlsanity.com/paper/2509.21360/) (2025)
- [Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection](https://mlsanity.com/paper/2504.17834/) (2025)

## Abstract (arXiv)

Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a person forms a mental model of the problem scenario before answering questions. Our research goal asks whether neural models can similarly benefit from envisioning the question scenario before answering a defeasible query. Our approach is, given a question, to have a model first create a graph of relevant influences, and then leverage that graph as an additional input when answering the question. Our system, CURIOUS, achieves a new state-of-the-art on three different defeasible reasoning datasets. This result is significant as it illustrates that performance can be improved by guiding a system to "think about" a question and explicitly model the scenario, rather than answering reflexively. Code, data, and pre-trained models are located at https://github.com/madaan/thinkaboutit.