# Explaining Interactions Between Text Spans

arXiv: https://arxiv.org/abs/2310.13506 · HTML: https://mlsanity.com/paper/2310.13506/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 20 Oct 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [The Shapley Taylor Interaction Index](https://mlsanity.com/paper/1902.05622/) (2019)
- [Self-Attention Attribution: Interpreting Information Interactions Inside Transformer](https://mlsanity.com/paper/2004.11207/) (2020)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [How does this interaction affect me? Interpretable attribution for feature interactions](https://mlsanity.com/paper/2006.10965/) (2020)
- [Faith-Shap: The Faithful Shapley Interaction Index](https://mlsanity.com/paper/2203.00870/) (2022)
- [Can neural networks understand monotonicity reasoning?](https://mlsanity.com/paper/1906.06448/) (2019)
- [SemEval-2020 Task 4: Commonsense Validation and Explanation](https://mlsanity.com/paper/2007.00236/) (2020)
- [Evaluating Saliency Methods for Neural Language Models](https://mlsanity.com/paper/2104.05824/) (2021)
- [A Survey of Community Search Over Big Graphs](https://mlsanity.com/paper/1904.12539/) (2019)
- [Connecting Attributions and QA Model Behavior on Realistic Counterfactuals](https://mlsanity.com/paper/2104.04515/) (2021)
- [Explanations of Black-Box Models based on Directional Feature Interactions](https://mlsanity.com/paper/2304.07670/) (2023)
- [Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks](https://mlsanity.com/paper/2104.04488/) (2021)
- [Attentive Tree-structured Network for Monotonicity Reasoning](https://mlsanity.com/paper/2101.00540/) (2021)

## Built on by (most cited first, 1 of 1)

- [Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models](https://mlsanity.com/paper/2510.02629/) (2025)

## Abstract (arXiv)

Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). However, existing highlight-based explanations primarily focus on identifying individual important tokens or interactions only between adjacent tokens or tuples of tokens. Most notably, there is a lack of annotations capturing the human decision-making process w.r.t. the necessary interactions for informed decision-making in such tasks. To bridge this gap, we introduce SpanEx, a multi-annotator dataset of human span interaction explanations for two NLU tasks: NLI and FC. We then investigate the decision-making processes of multiple fine-tuned large language models in terms of the employed connections between spans in separate parts of the input and compare them to the human reasoning processes. Finally, we present a novel community detection based unsupervised method to extract such interaction explanations from a model's inner workings.