mlsanityData to 7 Oct 2026

METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation

arXiv 2205.02593 ↗First posted 5 May 2022cs.CLcited by 17

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Knowing the reasoning chains from knowledge to the predicted answers can help construct an explainable question answering (QA) system. Advances on QA explanation propose to explain the answers with entailment trees composed of multiple entailment steps. While current work proposes to generate entailment trees with end-to-end generative models, the steps in the generated trees are not constrained and could be unreliable. In this paper, we propose METGEN, a Module-based Entailment Tree GENeration framework that has multiple modules and a reasoning controller. Given a question and several supporting knowledge, METGEN can iteratively generate the entailment tree by conducting single-step entailment with separate modules and selecting the reasoning flow with the controller. As each module is guided to perform a specific type of entailment reasoning, the steps generated by METGEN are more reliable and valid. Experiment results on the standard benchmark show that METGEN can outperform previous state-of-the-art models with only 9% of the parameters.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 37 of its 47 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

37 of 47 references.

References · 37

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  5. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  9. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  10. 2015Neural Module Networkscited by 375
  11. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  12. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
25 more
  1. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  2. 2020Transformers as Soft Reasoners over Languagecited by 265
  3. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 248
  4. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  5. 2021Explaining Answers with Entailment Treescited by 148
  6. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  7. 2017Learning to Reason: End-to-End Module Networks for Visual Question Answeringcited by 125
  8. 2019Neural Module Networks for Reasoning over Textcited by 65
  9. 2019Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answeringcited by 58
  10. 2020QED: A Framework and Dataset for Explanations in Question Answeringcited by 55
  11. 2020PRover: Proof Generation for Interpretable Reasoning over Rulescited by 53
  12. 2020Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answeringcited by 49
  13. 2020WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challengecited by 43
  14. 2019R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reasoncited by 36
  15. 2020Explaining Question Answering Models through Text Generationcited by 33
  16. 2020A Survey on Explainability in Machine Reading Comprehensioncited by 33
  17. 2021Flexible Generation of Natural Language Deductionscited by 28
  18. 2020Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answeringcited by 24
  19. 2020Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledgecited by 24
  20. 2020Teaching Machine Comprehension with Compositional Explanationscited by 22
  21. 2021multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoningcited by 15
  22. 2019Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehensioncited by 12
  23. 2018Neural Compositional Denotational Semantics for Question Answeringcited by 11
  24. 2020Autoregressive Reasoning over Chains of Facts with Transformerscited by 7
  25. 2021Do Answers to Boolean Questions Need Explanations? Yescited by 5

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 5; 2024: 5.

17 papers.

Sort:

By area:

  1. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  2. 2023Natural Language Reasoning, A Surveycited by 61
  3. 2024A Survey on Deep Learning for Theorem Provingcited by 55
  4. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  5. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  6. 2023RECKONING: Reasoning through Dynamic Knowledge Encodingcited by 17
  7. 2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoningcited by 16
  8. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  9. 2022Natural Language Deduction with Incomplete Informationcited by 12
  10. 2022RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Treescited by 7
  11. 2022MetaLogic: Logical Reasoning Explanations with Fine-Grained Structurecited by 3
  12. 2023Deductive Additivity for Planning of Natural Language Proofscited by 3
5 more
  1. 2024SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learningcited by 3
  2. 2024A Logical Pattern Memory Pre-trained Model for Entailment Tree Generationcited by 3
  3. 2023Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoningcited by 1
  4. 2024From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answeringcited by 1
  5. 2024Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
  2. 2022Active entailment encoding for explanation tree construction using parsimonious generation of hard negatives
  3. 2023Improving Question Generation with Multi-level Content Planning
  4. 2022Ask to Understand: Question Generation for Multi-hop Question Answering
  5. 2023IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions
  6. 2024An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism
  7. 2022QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation
  8. 2025TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering