# A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution

arXiv: https://arxiv.org/abs/2404.01921 · HTML: https://mlsanity.com/paper/2404.01921/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text](https://mlsanity.com/paper/2012.04698/) (2020)
- [GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective](https://mlsanity.com/paper/2211.08073/) (2022)
- [Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals](https://mlsanity.com/paper/2012.10040/) (2020)
- [Robustness to Spurious Correlations via Human Annotations](https://mlsanity.com/paper/2007.06661/) (2020)
- [Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution](https://mlsanity.com/paper/1906.01753/) (2019)
- [What if This Modified That? Syntactic Interventions via Counterfactual Embeddings](https://mlsanity.com/paper/2105.14002/) (2021)
- [Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization](https://mlsanity.com/paper/1805.10985/) (2018)
- [Supervised Knowledge Makes Large Language Models Better In-context Learners](https://mlsanity.com/paper/2312.15918/) (2023)
- [Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora](https://mlsanity.com/paper/2011.12249/) (2020)
- [Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling](https://mlsanity.com/paper/2009.11032/) (2020)
- [Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference](https://mlsanity.com/paper/2110.05362/) (2021)
- [Text Counterfactuals via Latent Optimization and Shapley-Guided Search](https://mlsanity.com/paper/2110.11589/) (2021)
- [2 * n is better than n2: Decomposing Event Coreference Resolution into Two Tractable Problems](https://mlsanity.com/paper/2305.05672/) (2023)

## Built on by (most cited first, 5 of 5)

- [Cross-Document Contextual Coreference Resolution in Knowledge Graphs](https://mlsanity.com/paper/2504.05767/) (2025)
- [Enhancing Coreference Resolution with Pretrained Language Models: Bridging the Gap Between Syntax and Semantics](https://mlsanity.com/paper/2504.05855/) (2025)
- [CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples](https://mlsanity.com/paper/2508.21083/) (2025)
- [Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering](https://mlsanity.com/paper/2505.02311/) (2025)
- [Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolution](https://mlsanity.com/paper/2506.01488/) (2025)

## Abstract (arXiv)

Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.