Teach Me to Explain: A Review of Datasets for Explainable NLP

By Sarah Wiegreffe, Ana Marasovic. 2021

70 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, neutral): “Another closely related direction uses natural language explanations (NLEs), often with the goal of improving model interpretability (Zhou et al., 2020; Wiegreffe and Marasovi´c, 2021, inter alia ).”
Few-Shot Self-Rationalization with Natural Language Prompts (2021, methodology): “…To identify available datasets suitable for few-shot self-rationalization, we start with a recent overview of datasets with free-text explanations (Wiegreffe and Marasovi´c, 2021) and ﬁl-ter them according to the following criteria: (i) the input is textual, (ii) the explanation consists of one…”
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations (2022, methodology): “…explanations (NLEs) to promote model reasoning, either by training a model to explain (Rajani et al., 2019; Camburu et al., 2018; Chen et al., 2022; Wiegreffe and Marasovi´c, 2021), or generating answers to templated queries and distantly supervised rationales (Shwartz et al., 2020; Brahman et…”
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning (2021, background): “Structured Explanations in NLP: Explanation datasets in NLP (Wiegreffe and Marasovi´c, 2021) take three major forms: (1) extractive rationales (Zaidan et al., 2007; Lei et al., 2016; Yu et al., 2019; DeYoung et al., 2020), (2) free-form or natural language explanations (Camburu et al., 2018; Rajani…”
Trustworthy AI: From Principles to Practices (2021, methodology): “To train the explanation task, it is helpful to consider collecting explanations or information that may not directly be part of the end task, either directly from annotators [354] or with the help of automated approaches [185].”
Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback (2021, unknown): “Still, there are several applications (Wiegreffe and Marasović, 2021) where our approach would currently apply”
Policy Compliance Detection via Expression Tree Inference (2022, methodology): “Furthermore, in our case, policies are decomposed into questions to provide a more explainable method for PCD as compared to entailment, task-speciﬁc explainablility has been explored in NLP (Kotonya and Toni, 2020; Wiegreffe and Marasovi´c, 2021).”