# Unsupervised Editing for Counterfactual Stories

arXiv: https://arxiv.org/abs/2112.05417 · HTML: https://mlsanity.com/paper/2112.05417/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Story Ending Generation with Incremental Encoding and Commonsense Knowledge](https://mlsanity.com/paper/1808.10113/) (2018)
- [Evaluating Coherence in Dialogue Systems using Entailment](https://mlsanity.com/paper/1904.03371/) (2019)
- [A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation](https://mlsanity.com/paper/1808.06945/) (2018)
- [Unsupervised Paraphrasing by Simulated Annealing](https://mlsanity.com/paper/1909.03588/) (2019)
- [Challenges of Using Text Classifiers for Causal Inference](https://mlsanity.com/paper/1810.00956/) (2018)
- [Deep Generative Models with Learnable Knowledge Constraints](https://mlsanity.com/paper/1806.09764/) (2018)
- [Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach](https://mlsanity.com/paper/2010.06792/) (2020)
- [AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples](https://mlsanity.com/paper/1805.04680/) (2018)
- [Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet](https://mlsanity.com/paper/2109.05797/) (2021)
- [Sketch and Customize: A Counterfactual Story Generator](https://mlsanity.com/paper/2104.00929/) (2021)

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

- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [Converge to the Truth: Factual Error Correction via Iterative Constrained Editing](https://mlsanity.com/paper/2211.12130/) (2022)
- [Causality-aware Concept Extraction based on Knowledge-guided Prompting](https://mlsanity.com/paper/2305.01876/) (2023)
- [Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues](https://mlsanity.com/paper/2210.16838/) (2022)
- [Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario](https://mlsanity.com/paper/2210.11431/) (2022)
- [Unsupervised Explanation Generation via Correct Instantiations](https://mlsanity.com/paper/2211.11160/) (2022)
- [SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator](https://mlsanity.com/paper/2403.11833/) (2024)
- [DTO: a Differentiable Training Objective for Effective Counterfactual Story Rewriting](https://mlsanity.com/paper/2605.24885/) (2026)

## Abstract (arXiv)

Creating what-if stories requires reasoning about prior statements and possible outcomes of the changed conditions. One can easily generate coherent endings under new conditions, but it would be challenging for current systems to do it with minimal changes to the original story. Therefore, one major challenge is the trade-off between generating a logical story and rewriting with minimal-edits. In this paper, we propose EDUCAT, an editing-based unsupervised approach for counterfactual story rewriting. EDUCAT includes a target position detection strategy based on estimating causal effects of the what-if conditions, which keeps the causal invariant parts of the story. EDUCAT then generates the stories under fluency, coherence and minimal-edits constraints. We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off. We evaluate EDUCAT on a public counterfactual story rewriting benchmark. Experiments show that EDUCAT achieves the best trade-off over unsupervised SOTA methods according to both automatic and human evaluation. The resources of EDUCAT are available at: https://github.com/jiangjiechen/EDUCAT.