mlsanityData to 7 Oct 2026

Natural Language Deduction through Search over Statement Compositions

arXiv 2201.06028 ↗First posted 16 Jan 2022cs.CL cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis. Existing methods primarily focus on the end-to-end discriminative version of this task, but less work has treated the generative version in which a model searches over the space of statements entailed by the premises to constructively derive the hypothesis. We propose a system for doing this kind of deductive reasoning in natural language by decomposing the task into separate steps coordinated by a search procedure, producing a tree of intermediate conclusions that faithfully reflects the system's reasoning process. Our experiments on the EntailmentBank dataset (Dalvi et al., 2021) demonstrate that the proposed system can successfully prove true statements while rejecting false ones. Moreover, it produces natural language explanations with a 17% absolute higher step validity than those produced by an end-to-end T5 model.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 16 Jan 2022.

Builds on

27 of 38 references.

References · 27

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  7. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  8. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  9. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  10. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  11. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  12. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
15 more
  1. 2020What Can We Learn from Collective Human Opinions on Natural Language Inference Data?cited by 148
  2. 2021Explaining Answers with Entailment Treescited by 148
  3. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  4. 2020PRover: Proof Generation for Interpretable Reasoning over Rulescited by 53
  5. 2019Multi-hop Question Answering via Reasoning Chainscited by 42
  6. 2019Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extractioncited by 39
  7. 2019NLProlog: Reasoning with Weak Unification for Question Answering in Natural Languagecited by 36
  8. 2019Uncertain Natural Language Inferencecited by 35
  9. 2020Conversational Neuro-Symbolic Commonsense Reasoningcited by 28
  10. 2021Flexible Generation of Natural Language Deductionscited by 28
  11. 2021Learning with Different Amounts of Annotation: From Zero to Many Labelscited by 28
  12. 2021NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoningcited by 24
  13. 2019MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicitycited by 20
  14. 2021multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoningcited by 15
  15. 2021DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 17; 2023: 10; 2024: 7; 2025: 0; 2026: 1.

35 papers.

Sort:

By area:

  1. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  2. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  3. 2022Faithful Reasoning Using Large Language Modelscited by 130
  4. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  5. 2022Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Trainingcited by 88
  6. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  7. 2024A Survey on Deep Learning for Theorem Provingcited by 55
  8. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  9. 2023Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statementscited by 44
  10. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  11. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  12. 2024Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Provingcited by 35
23 more
  1. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  2. 2023Logical Reasoning over Natural Language as Knowledge Representation: A Surveycited by 32
  3. 2024Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatabilitycited by 22
  4. 2022Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Modelcited by 20
  5. 2023Learning Deductive Reasoning from Synthetic Corpus based on Formal Logiccited by 18
  6. 2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoningcited by 16
  7. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  8. 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
  9. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  10. 2022Natural Language Deduction with Incomplete Informationcited by 12
  11. 2023Explicit Planning Helps Language Models in Logical Reasoningcited by 12
  12. 2024Enhancing Systematic Decompositional Natural Language Inference Using Informal Logiccited by 12
  13. 2024SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMscited by 8
  14. 2022RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Treescited by 7
  15. 2022MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generationcited by 7
  16. 2022Breakpoint Transformers for Modeling and Tracking Intermediate Beliefscited by 6
  17. 2022Best-k Search Algorithm for Neural Text Generationcited by 6
  18. 2023Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solvingcited by 4
  19. 2023Deductive Additivity for Planning of Natural Language Proofscited by 3
  20. 2024Can Separators Improve Chain-of-Thought Prompting?cited by 2
  21. 2023Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoningcited by 1
  22. 2024From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answeringcited by 1
  23. 2026Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Formal Proofs as Structured Explanations: Proposing Several Tasks on Explainable Natural Language Inference
  2. 2024Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning
  3. 2025Reasoning-Grounded Natural Language Explanations for Language Models
  4. 2026Learning to Reason Efficiently with A* Post-Training
  5. 2026Decompose-and-Formalise: Recursively Verifiable Natural Language Inference
  6. 2025Toward Honest Language Models for Deductive Reasoning
  7. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
  8. 2024Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning