# Shrome at Touch'e: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction

arXiv: https://arxiv.org/abs/2610.03268 · HTML: https://mlsanity.com/paper/2610.03268/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [An Analysis of Simple Data Augmentation for Named Entity Recognition](https://mlsanity.com/paper/2010.11683/) (2020)
- [Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.06804/) (2021)
- [The Causal News Corpus: Annotating Causal Relations in Event Sentences from News](https://mlsanity.com/paper/2204.11714/) (2022)
- [Boundary Smoothing for Named Entity Recognition](https://mlsanity.com/paper/2204.12031/) (2022)
- [UniCausal: Unified Benchmark and Repository for Causal Text Mining](https://mlsanity.com/paper/2208.09163/) (2022)
- [Event Causality Identification with Causal News Corpus -- Shared Task 3, CASE 2022](https://mlsanity.com/paper/2211.12154/) (2022)
- [BoschAI @ Causal News Corpus 2023: Robust Cause-Effect Span Extraction using Multi-Layer Sequence Tagging and Data Augmentation](https://mlsanity.com/paper/2312.06338/) (2023)
- [Investigating Counterclaims in Causality Extraction from Text](https://mlsanity.com/paper/2510.08224/) (2025)

## Abstract (arXiv)

Touch'e 2026 extends causality extraction to counter-causal claims: news sentences whose surface form appears causal but whose meaning denies the causation, as in "It is falsely believed that X caused Y." A system that relies on surface cues such as "caused" or "led to" will accept such a sentence as causal and give it the wrong polarity. On the Countercausal News Corpus (CCNC), the task has three subtasks: deciding whether a sentence is causal (detection), locating its cause and effect spans (extraction), and labeling its polarity as procausal, counter-causal, or uncausal. We build one model per subtask. Detection is a fine-tuned classifier with a single cross-task rule that uses the extracted spans to remove false positives. For extraction, we ensemble three RoBERTa-large BILOU+CRF taggers by averaging their token-level scores before decoding, rather than voting on the spans each tagger produces. For polarity, where labeled counter-causal examples are scarcest, we add training sentences generated by a large language model prompted with nine patterns of counter-causal expression adapted from Hagen et al., keeping only those that pass automatic structural checks. On the held-out CCNC test set, the system reaches F1 0.869 on detection and macro-F1 0.817 on polarity, and in the organizers' final causal-only evaluation of extraction it scores granularity-adjusted F1 0.728, the highest extraction score among all submissions including the organizers' baseline. The development split is used only for component selection and the ablations reported in the paper.