# Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE

arXiv: https://arxiv.org/abs/2210.16407 · HTML: https://mlsanity.com/paper/2210.16407/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://mlsanity.com/paper/2010.04119/) (2020)
- [FLUTE: Figurative Language Understanding through Textual Explanations](https://mlsanity.com/paper/2205.12404/) (2022)
- [Figurative Language in Recognizing Textual Entailment](https://mlsanity.com/paper/2106.01195/) (2021)
- [DREAM: Improving Situational QA by First Elaborating the Situation](https://mlsanity.com/paper/2112.08656/) (2021)

## Built on by (most cited first, 8 of 8)

- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs](https://mlsanity.com/paper/2410.13648/) (2024)
- [Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment](https://mlsanity.com/paper/2305.14492/) (2023)
- [Do language models have coherent mental models of everyday things?](https://mlsanity.com/paper/2212.10029/) (2022)
- [Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection](https://mlsanity.com/paper/2405.09279/) (2024)
- [ExpressivityBench: Can LLMs Communicate Implicitly?](https://mlsanity.com/paper/2411.08010/) (2024)
- [Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs](https://mlsanity.com/paper/2405.08760/) (2024)
- [(RSA)2: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding](https://mlsanity.com/paper/2506.09301/) (2025)

## Abstract (arXiv)

Figurative language (e.g., "he flew like the wind") is challenging to understand, as it is hard to tell what implicit information is being conveyed from the surface form alone. We hypothesize that to perform this task well, the reader needs to mentally elaborate the scene being described to identify a sensible meaning of the language. We present DREAM-FLUTE, a figurative language understanding system that does this, first forming a "mental model" of situations described in a premise and hypothesis before making an entailment/contradiction decision and generating an explanation. DREAM-FLUTE uses an existing scene elaboration model, DREAM, for constructing its "mental model." In the FigLang2022 Shared Task evaluation, DREAM-FLUTE achieved (joint) first place (Acc@60=63.3%), and can perform even better with ensemble techniques, demonstrating the effectiveness of this approach. More generally, this work suggests that adding a reflective component to pretrained language models can improve their performance beyond standard fine-tuning (3.3% improvement in Acc@60).