# DREAM: Improving Situational QA by First Elaborating the Situation

arXiv: https://arxiv.org/abs/2112.08656 · HTML: https://mlsanity.com/paper/2112.08656/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 16 Dec 2021.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines](https://mlsanity.com/paper/2006.04884/) (2020)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [Reasoning Over Paragraph Effects in Situations](https://mlsanity.com/paper/1908.05852/) (2019)
- [Modeling Naive Psychology of Characters in Simple Commonsense Stories](https://mlsanity.com/paper/1805.06533/) (2018)
- [Generating Natural Questions About an Image](https://mlsanity.com/paper/1603.06059/) (2016)
- [General-Purpose Question-Answering with Macaw](https://mlsanity.com/paper/2109.02593/) (2021)
- [BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA](https://mlsanity.com/paper/2005.00766/) (2020)
- [Inquisitive Question Generation for High Level Text Comprehension](https://mlsanity.com/paper/2010.01657/) (2020)
- [Improving Machine Reading Comprehension with General Reading Strategies](https://mlsanity.com/paper/1810.13441/) (2018)
- [Think about it! Improving defeasible reasoning by first modeling the question scenario](https://mlsanity.com/paper/2110.12349/) (2021)
- [Towards General Natural Language Understanding with Probabilistic Worldbuilding](https://mlsanity.com/paper/2105.02486/) (2021)
- [Contextualized Scene Imagination for Generative Commonsense Reasoning](https://mlsanity.com/paper/2112.06318/) (2021)

## Built on by (most cited first, 18 of 18)

- [SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs](https://mlsanity.com/paper/2410.13648/) (2024)
- [NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly](https://mlsanity.com/paper/2210.08604/) (2022)
- [Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering](https://mlsanity.com/paper/2210.03078/) (2022)
- [NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation](https://mlsanity.com/paper/2310.14563/) (2023)
- [SocialDial: A Benchmark for Socially-Aware Dialogue Systems](https://mlsanity.com/paper/2304.12026/) (2023)
- [Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment](https://mlsanity.com/paper/2305.14492/) (2023)
- [Crystal: Introspective Reasoners Reinforced with Self-Feedback](https://mlsanity.com/paper/2310.04921/) (2023)
- [Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research](https://mlsanity.com/paper/2310.13915/) (2023)
- [RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations](https://mlsanity.com/paper/2402.11178/) (2024)
- [Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety](https://mlsanity.com/paper/2212.06295/) (2022)
- [Do language models have coherent mental models of everyday things?](https://mlsanity.com/paper/2212.10029/) (2022)
- [Evaluating Subjective Cognitive Appraisals of Emotions from Large Language Models](https://mlsanity.com/paper/2310.14389/) (2023)
- [Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE](https://mlsanity.com/paper/2210.16407/) (2022)
- [CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems](https://mlsanity.com/paper/2406.17300/) (2024)
- [Digital Socrates: Evaluating LLMs through Explanation Critiques](https://mlsanity.com/paper/2311.09613/) (2023)
- [MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detection](https://mlsanity.com/paper/2511.09918/) (2025)
- [Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?](https://mlsanity.com/paper/2402.14355/) (2024)
- [Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning](https://mlsanity.com/paper/2605.22542/) (2026)

## Abstract (arXiv)

When people answer questions about a specific situation, e.g., "I cheated on my mid-term exam last week. Was that wrong?", cognitive science suggests that they form a mental picture of that situation before answering. While we do not know how language models (LMs) answer such questions, we conjecture that they may answer more accurately if they are also provided with additional details about the question situation, elaborating the "scene". To test this conjecture, we train a new model, DREAM, to answer questions that elaborate the scenes that situated questions are about, and then provide those elaborations as additional context to a question-answering (QA) model. We find that DREAM is able to create better scene elaborations (more accurate, useful, and consistent) than a representative state-of-the-art, zero-shot model (Macaw). We also find that using the scene elaborations as additional context improves the answer accuracy of a downstream QA system, including beyond that obtainable by simply further finetuning the QA system on DREAM's training data. These results suggest that adding focused elaborations about a situation can improve a system's reasoning about it, and may serve as an effective way of injecting new scenario based knowledge into QA models. Finally, our approach is dataset-neutral; we observe improved QA performance across different models, with even bigger gains on models with fewer parameters. We make our dataset and model publicly available at https://github.com/allenai/dream.