# Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

arXiv: https://arxiv.org/abs/2205.01809 · HTML: https://mlsanity.com/paper/2205.01809/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 68 references that are in the map.
- First posted on arXiv 3 May 2022.

## Builds on (most cited first, 18 of 18)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations](https://mlsanity.com/paper/1910.03065/) (2019)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference](https://mlsanity.com/paper/1802.03052/) (2018)
- [Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering](https://mlsanity.com/paper/2010.03274/) (2020)
- [A Study of Automatic Metrics for the Evaluation of Natural Language Explanations](https://mlsanity.com/paper/2103.08545/) (2021)
- [A Survey on Explainability in Machine Reading Comprehension](https://mlsanity.com/paper/2010.00389/) (2020)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration](https://mlsanity.com/paper/2107.11879/) (2021)
- [Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards](https://mlsanity.com/paper/2105.01974/) (2021)
- [On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings](https://mlsanity.com/paper/2109.03334/) (2021)
- [Case-Based Abductive Natural Language Inference](https://mlsanity.com/paper/2009.14539/) (2020)
- [Identifying and Explaining Discriminative Attributes](https://mlsanity.com/paper/1909.05363/) (2019)

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

- [On the Importance and Evaluation of Narrativity in Natural Language AI Explanations](https://mlsanity.com/paper/2604.18311/) (2026)

## Abstract (arXiv)

A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations. However, the methodologies to design and evaluate explanation-based inference models are still poorly informed by theoretical accounts on the nature of explanation. As an attempt to provide an epistemologically grounded characterisation for XAI, this paper focuses on the scientific domain, aiming to bridge the gap between theory and practice on the notion of a scientific explanation. Specifically, the paper combines a detailed survey of the modern accounts of scientific explanation in Philosophy of Science with a systematic analysis of corpora of natural language explanations, clarifying the nature and function of explanatory arguments from both a top-down (categorical) and a bottom-up (corpus-based) perspective. Through a mixture of quantitative and qualitative methodologies, the presented study allows deriving the following main conclusions: (1) Explanations cannot be entirely characterised in terms of inductive or deductive arguments as their main function is to perform unification; (2) An explanation must cite causes and mechanisms that are responsible for the occurrence of the event to be explained; (3) While natural language explanations possess an intrinsic causal-mechanistic nature, they are not limited to causes and mechanisms, also accounting for pragmatic elements such as definitions, properties and taxonomic relations; (4) Patterns of unification naturally emerge in corpora of explanations even if not intentionally modelled; (5) Unification is realised through a process of abstraction, whose function is to provide the inference substrate for subsuming the event to be explained under recurring patterns and high-level regularities.