mlsanityData to 7 Oct 2026

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

arXiv 2205.09224 ↗First posted 18 May 2022cs.CLcited by 26

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

Abstract (arXiv)

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.

Key facts. Cited by 26 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 22 of its 32 references that are in the map. First posted on arXiv 18 May 2022.

Builds on

22 of 32 references.

References · 22

  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. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  8. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  9. 2019Attention is not Explanationcited by 916
  10. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  11. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  12. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
10 more
  1. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  2. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  3. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  4. 2021Explaining Answers with Entailment Treescited by 148
  5. 2020Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answeringcited by 49
  6. 2020Learning-to-Rank with BERT in TF-Rankingcited by 36
  7. 2021Flexible Generation of Natural Language Deductionscited by 28
  8. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  9. 2021Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regenerationcited by 17
  10. 2020Autoregressive Reasoning over Chains of Facts with Transformerscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 9; 2023: 7; 2024: 9; 2025: 1.

26 papers.

Sort:

By area:

  1. 2022Faithful Reasoning Using Large Language Modelscited by 130
  2. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  3. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  4. 2023Natural Language Reasoning, A Surveycited by 61
  5. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  6. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  7. 2024Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Provingcited by 35
  8. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  9. 2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoningcited by 16
  10. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  11. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  12. 2023STREET: A Multi-Task Structured Reasoning and Explanation Benchmarkcited by 13
14 more
  1. 2022Natural Language Deduction with Incomplete Informationcited by 12
  2. 2024Enhancing Systematic Decompositional Natural Language Inference Using Informal Logiccited by 12
  3. 2022RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Treescited by 7
  4. 2023Deductive Additivity for Planning of Natural Language Proofscited by 3
  5. 2024SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learningcited by 3
  6. 2024A Logical Pattern Memory Pre-trained Model for Entailment Tree Generationcited by 3
  7. 2024An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanismcited by 3
  8. 2023Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labelscited by 2
  9. 2023Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoningcited by 1
  10. 2024From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answeringcited by 1
  11. 2025HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 1
  12. 2022Active entailment encoding for explanation tree construction using parsimonious generation of hard negativescited by 0
  13. 2024LogicPrpBank: A Corpus for Logical Implication and Equivalencecited by 0
  14. 2024Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation
  2. 2025TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering
  3. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models
  4. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  5. 2026EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
  6. 2026Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
  7. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  8. 2025KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation