mlsanityData to 14 Oct 2026

Explaining Answers with Entailment Trees

arXiv 2104.08661 ↗First posted 17 Apr 2021cs.CL cs.AIcited by 152

Not on the map. Why?

Cited by 72 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If this could be done, new opportunities for understanding and debugging the system's reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees. Given a hypothesis (question + answer), we define three increasingly difficult explanation tasks: generate a valid entailment tree given (a) all relevant sentences (b) all relevant and some irrelevant sentences, or (c) a corpus. We show that a strong language model can partially solve these tasks, in particular when the relevant sentences are included in the input (e.g., 35% of trees for (a) are perfect), and with indications of generalization to other domains. This work is significant as it provides a new type of dataset (multistep entailments) and baselines, offering a new avenue for the community to generate richer, more systematic explanations.

Key facts. Cited by 152 papers in the map (data through 14 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

28 of 34 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  8. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  9. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  10. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  11. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  12. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
16 more
  1. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  2. 2020Generative Language Modeling for Automated Theorem Provingcited by 388
  3. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  4. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  5. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  6. 2018Transforming Question Answering Datasets Into Natural Language Inference Datasetscited by 99
  7. 2018WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inferencecited by 60
  8. 2018Training Classifiers with Natural Language Explanationscited by 58
  9. 2020PRover: Proof Generation for Interpretable Reasoning over Rulescited by 53
  10. 2020Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answeringcited by 49
  11. 2020Learning to Prove Theorems by Learning to Generate Theoremscited by 43
  12. 2019R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reasoncited by 36
  13. 2020Learning-to-Rank with BERT in TF-Rankingcited by 36
  14. 2019Finding Generalizable Evidence by Learning to Convince Q&A Modelscited by 25
  15. 2020Teaching Machine Comprehension with Compositional Explanationscited by 22
  16. 2017Natural Language Inference from Multiple Premisescited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 41; 2023: 39; 2024: 32; 2025: 21; 2026: 14.

152 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  3. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  4. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  6. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  7. 2022Reasoning with Language Model Prompting: A Surveycited by 252
  8. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 177
  9. 2022Faithful Reasoning Using Large Language Modelscited by 130
  10. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  11. 2023GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoningcited by 108
  12. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
38 more
  1. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 97
  2. 2023Shepherd: A Critic for Language Model Generationcited by 97
  3. 2023ReCEval: Evaluating Reasoning Chains via Correctness and Informativenesscited by 77
  4. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  5. 2025The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systemscited by 72
  6. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Modelscited by 70
  7. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  8. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  9. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 65
  10. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  11. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 63
  12. 2023Natural Language Reasoning, A Surveycited by 61
  13. 2023T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answeringcited by 60
  14. 2024A Survey on Deep Learning for Theorem Provingcited by 57
  15. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  16. 2023BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Informationcited by 44
  17. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  18. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  19. 2022Natural Language Deduction through Search over Statement Compositionscited by 35
  20. 2023GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Promptscited by 34
  21. 2024Data-driven Discovery with Large Generative Modelscited by 34
  22. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  23. 2024A Survey of Useful LLM Evaluationcited by 29
  24. 2024Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMscited by 29
  25. 2024Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpuscited by 29
  26. 2021Flexible Generation of Natural Language Deductionscited by 28
  27. 2023SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluationcited by 27
  28. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasonercited by 26
  29. 2023ThoughtSource: A central hub for large language model reasoning datacited by 23
  30. 2024Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Taskscited by 23
  31. 2024Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Modelcited by 23
  32. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  33. 2024A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagationcited by 21
  34. 2022Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Modelcited by 20
  35. 2024Quantifying the Capabilities of LLMs across Scale and Precisioncited by 19
  36. 2023RECKONING: Reasoning through Dynamic Knowledge Encodingcited by 18
  37. 2023Learning Deductive Reasoning from Synthetic Corpus based on Formal Logiccited by 18
  38. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17

50 most cited of 152 All 152 (JSON)