# Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering

arXiv: https://arxiv.org/abs/2010.03274 · HTML: https://mlsanity.com/paper/2010.03274/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 30 of 49)

- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [LAMBADA: Backward Chaining for Automated Reasoning in Natural Language](https://mlsanity.com/paper/2212.13894/) (2022)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)
- [e-CARE: a New Dataset for Exploring Explainable Causal Reasoning](https://mlsanity.com/paper/2205.05849/) (2022)
- [Why Machine Reading Comprehension Models Learn Shortcuts?](https://mlsanity.com/paper/2106.01024/) (2021)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning](https://mlsanity.com/paper/2203.08480/) (2022)
- [Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner](https://mlsanity.com/paper/2205.09224/) (2022)
- [Social Genome: Grounded Social Reasoning Abilities of Multimodal Models](https://mlsanity.com/paper/2502.15109/) (2025)
- [GNN is a Counter? Revisiting GNN for Question Answering](https://mlsanity.com/paper/2110.03192/) (2021)
- [WikiWhy: Answering and Explaining Cause-and-Effect Questions](https://mlsanity.com/paper/2210.12152/) (2022)
- [Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration](https://mlsanity.com/paper/2107.11879/) (2021)
- [METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation](https://mlsanity.com/paper/2205.02593/) (2022)
- [NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning](https://mlsanity.com/paper/2209.07662/) (2022)
- [multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning](https://mlsanity.com/paper/2106.01354/) (2021)
- [Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis](https://mlsanity.com/paper/2309.05217/) (2023)
- [Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety](https://mlsanity.com/paper/2212.06295/) (2022)
- [STREET: A Multi-Task Structured Reasoning and Explanation Benchmark](https://mlsanity.com/paper/2302.06729/) (2023)
- [Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards](https://mlsanity.com/paper/2105.01974/) (2021)
- [Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability](https://mlsanity.com/paper/2104.06751/) (2021)
- [On Evaluating Explanation Utility for Human-AI Decision Making in NLP](https://mlsanity.com/paper/2407.03545/) (2024)
- [RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees](https://mlsanity.com/paper/2210.17095/) (2022)
- [Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2305.08135/) (2023)
- [On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings](https://mlsanity.com/paper/2109.03334/) (2021)

## Abstract (arXiv)

Despite the rapid progress in multihop question-answering (QA), models still have trouble explaining why an answer is correct, with limited explanation training data available to learn from. To address this, we introduce three explanation datasets in which explanations formed from corpus facts are annotated. Our first dataset, eQASC, contains over 98K explanation annotations for the multihop question answering dataset QASC, and is the first that annotates multiple candidate explanations for each answer. The second dataset eQASC-perturbed is constructed by crowd-sourcing perturbations (while preserving their validity) of a subset of explanations in QASC, to test consistency and generalization of explanation prediction models. The third dataset eOBQA is constructed by adding explanation annotations to the OBQA dataset to test generalization of models trained on eQASC. We show that this data can be used to significantly improve explanation quality (+14% absolute F1 over a strong retrieval baseline) using a BERT-based classifier, but still behind the upper bound, offering a new challenge for future research. We also explore a delexicalized chain representation in which repeated noun phrases are replaced by variables, thus turning them into generalized reasoning chains (for example: "X is a Y" AND "Y has Z" IMPLIES "X has Z"). We find that generalized chains maintain performance while also being more robust to certain perturbations.