# NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning

arXiv: https://arxiv.org/abs/2105.14167 · HTML: https://mlsanity.com/paper/2105.14167/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 29 May 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [SenseBERT: Driving Some Sense into BERT](https://mlsanity.com/paper/1908.05646/) (2019)
- [Can neural networks understand monotonicity reasoning?](https://mlsanity.com/paper/1906.06448/) (2019)
- [HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning](https://mlsanity.com/paper/1904.12166/) (2019)
- [MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity](https://mlsanity.com/paper/1910.08772/) (2019)
- [LangPro: Natural Language Theorem Prover](https://mlsanity.com/paper/1708.09417/) (2017)
- [Acquisition of Phrase Correspondences using Natural Deduction Proofs](https://mlsanity.com/paper/1804.07656/) (2018)
- [Representing Meaning with a Combination of Logical and Distributional Models](https://mlsanity.com/paper/1505.06816/) (2015)
- [Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference](https://mlsanity.com/paper/2010.15909/) (2020)
- [Monotonicity Marking from Universal Dependency Trees](https://mlsanity.com/paper/2104.08659/) (2021)
- [Combining Event Semantics and Degree Semantics for Natural Language Inference](https://mlsanity.com/paper/2011.00961/) (2020)
- [Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching](https://mlsanity.com/paper/1701.02149/) (2017)

## Built on by (most cited first, 25 of 25)

- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review](https://mlsanity.com/paper/2202.12205/) (2022)
- [Natural Language Deduction through Search over Statement Compositions](https://mlsanity.com/paper/2201.06028/) (2022)
- [Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models](https://mlsanity.com/paper/2205.11432/) (2022)
- [RECKONING: Reasoning through Dynamic Knowledge Encoding](https://mlsanity.com/paper/2305.06349/) (2023)
- [ARGUS: Hallucination and Omission Evaluation in Video-LLMs](https://mlsanity.com/paper/2506.07371/) (2025)
- [Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic](https://mlsanity.com/paper/2109.08927/) (2021)
- [Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference](https://mlsanity.com/paper/2203.04857/) (2022)
- [PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers](https://mlsanity.com/paper/2112.09237/) (2021)
- [A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus](https://mlsanity.com/paper/2405.11877/) (2024)
- [Data-Efficient Learning with Neural Programs](https://mlsanity.com/paper/2406.06246/) (2024)
- [Probing Linguistic Information For Logical Inference In Pre-trained Language Models](https://mlsanity.com/paper/2112.01753/) (2021)
- [Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations](https://mlsanity.com/paper/2502.11269/) (2025)
- [Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning](https://mlsanity.com/paper/2410.03348/) (2024)
- [Decomposing Natural Logic Inferences in Neural NLI](https://mlsanity.com/paper/2112.08289/) (2021)
- [Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming](https://mlsanity.com/paper/2503.21937/) (2025)
- [NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic](https://mlsanity.com/paper/2307.02849/) (2023)
- [Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks](https://mlsanity.com/paper/2502.04797/) (2025)
- [When Does Meaning Backfire? Investigating the Role of AMRs in NLI](https://mlsanity.com/paper/2506.14613/) (2025)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)
- [The Path to Autonomous Learners](https://mlsanity.com/paper/2211.02403/) (2022)
- [Extracting Mathematical Concepts with Large Language Models](https://mlsanity.com/paper/2309.00642/) (2023)
- [Quantum NLP models on Natural Language Inference](https://mlsanity.com/paper/2510.15972/) (2025)
- [Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs](https://mlsanity.com/paper/2609.32491/) (2026)
- [Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI](https://mlsanity.com/paper/2610.15158/) (2026)

## Abstract (arXiv)

Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have their advantages and weaknesses. However, currently, no method combines them in a system to solve the task of NLI. To merge symbolic and deep learning methods, we propose an inference framework called NeuralLog, which utilizes both a monotonicity-based logical inference engine and a neural network language model for phrase alignment. Our framework models the NLI task as a classic search problem and uses the beam search algorithm to search for optimal inference paths. Experiments show that our joint logic and neural inference system improves accuracy on the NLI task and can achieve state-of-art accuracy on the SICK and MED datasets.