# Flexible Generation of Natural Language Deductions

arXiv: https://arxiv.org/abs/2104.08825 · HTML: https://mlsanity.com/paper/2104.08825/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 62 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 30 of 34)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://mlsanity.com/paper/2009.00751/) (2020)
- [A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](https://mlsanity.com/paper/2005.05257/) (2020)
- [PRover: Proof Generation for Interpretable Reasoning over Rules](https://mlsanity.com/paper/2010.02830/) (2020)
- [Understanding Dataset Design Choices for Multi-hop Reasoning](https://mlsanity.com/paper/1904.12106/) (2019)
- [NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language](https://mlsanity.com/paper/1906.06187/) (2019)
- [Towards Robustifying NLI Models Against Lexical Dataset Biases](https://mlsanity.com/paper/2005.04732/) (2020)
- [Explaining Question Answering Models through Text Generation](https://mlsanity.com/paper/2004.05569/) (2020)
- [Critical Thinking for Language Models](https://mlsanity.com/paper/2009.07185/) (2020)
- [Conversational Neuro-Symbolic Commonsense Reasoning](https://mlsanity.com/paper/2006.10022/) (2020)

## Built on by (most cited first, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [NaturalProver: Grounded Mathematical Proof Generation with Language Models](https://mlsanity.com/paper/2205.12910/) (2022)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning](https://mlsanity.com/paper/2210.12217/) (2022)
- [Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement](https://mlsanity.com/paper/2204.13074/) (2022)
- [What do tokens know about their characters and how do they know it?](https://mlsanity.com/paper/2206.02608/) (2022)
- [Natural Language Deduction through Search over Statement Compositions](https://mlsanity.com/paper/2201.06028/) (2022)
- [Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus](https://mlsanity.com/paper/2411.12498/) (2024)
- [Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner](https://mlsanity.com/paper/2205.09224/) (2022)
- [Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic](https://mlsanity.com/paper/2308.07336/) (2023)
- [METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation](https://mlsanity.com/paper/2205.02593/) (2022)
- [Natural Language Deduction with Incomplete Information](https://mlsanity.com/paper/2211.00614/) (2022)
- [Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations](https://mlsanity.com/paper/2305.14618/) (2023)
- [VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks](https://mlsanity.com/paper/2511.04662/) (2025)
- [Learning Symbolic Rules for Reasoning in Quasi-Natural Language](https://mlsanity.com/paper/2111.12038/) (2021)
- [RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees](https://mlsanity.com/paper/2210.17095/) (2022)
- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives](https://mlsanity.com/paper/2406.12084/) (2024)
- [Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder](https://mlsanity.com/paper/2210.06230/) (2022)
- [Can Pretrained Language Models (Yet) Reason Deductively?](https://mlsanity.com/paper/2210.06442/) (2022)
- [Plug-and-Play Recipe Generation with Content Planning](https://mlsanity.com/paper/2212.05093/) (2022)
- [Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review](https://mlsanity.com/paper/2212.03747/) (2022)
- [Deductive Additivity for Planning of Natural Language Proofs](https://mlsanity.com/paper/2307.02472/) (2023)
- [A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation](https://mlsanity.com/paper/2403.06410/) (2024)

## Abstract (arXiv)

An interpretable system for open-domain reasoning needs to express its reasoning process in a transparent form. Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to understand. However, manipulating natural language statements in logically consistent ways is hard: models must cope with variation in how meaning is expressed while remaining precise. In this paper, we describe ParaPattern, a method for building models to generate deductive inferences from diverse natural language inputs without direct human supervision. We train BART-based models (Lewis et al., 2020) to generate the result of applying a particular logical operation to one or more premise statements. Crucially, we develop a largely automated pipeline for constructing suitable training examples from Wikipedia. We evaluate our models using out-of-domain sentence compositions from the QASC (Khot et al., 2020) and EntailmentBank (Dalvi et al., 2021) datasets as well as targeted perturbation sets. Our results show that our models are substantially more accurate and flexible than baseline systems. ParaPattern achieves 85% validity on examples of the 'substitution' operation from EntailmentBank without the use of any in-domain training data, matching the performance of a model fine-tuned for EntailmentBank. The full source code for our method is publicly available.