# Can Transformers Reason in Fragments of Natural Language?

arXiv: https://arxiv.org/abs/2211.05417 · HTML: https://mlsanity.com/paper/2211.05417/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 10 Nov 2022.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [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)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Semidefinite relaxations for certifying robustness to adversarial examples](https://mlsanity.com/paper/1811.01057/) (2018)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Robustness Verification for Transformers](https://mlsanity.com/paper/2002.06622/) (2020)
- [Probing Natural Language Inference Models through Semantic Fragments](https://mlsanity.com/paper/1909.07521/) (2019)
- [What Makes Reading Comprehension Questions Easier?](https://mlsanity.com/paper/1808.09384/) (2018)
- [Probing Linguistic Systematicity](https://mlsanity.com/paper/2005.04315/) (2020)
- [Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?](https://mlsanity.com/paper/2004.14839/) (2020)
- [Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge](https://mlsanity.com/paper/2006.06609/) (2020)
- [Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets](https://mlsanity.com/paper/1910.09302/) (2019)
- [A Framework for Evaluation of Machine Reading Comprehension Gold Standards](https://mlsanity.com/paper/2003.04642/) (2020)
- [Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability](https://mlsanity.com/paper/2112.09054/) (2021)

## Built on by (most cited first, 8 of 8)

- [ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning](https://mlsanity.com/paper/2502.01100/) (2025)
- [LAMBADA: Backward Chaining for Automated Reasoning in Natural Language](https://mlsanity.com/paper/2212.13894/) (2022)
- [Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents](https://mlsanity.com/paper/2310.09343/) (2023)
- [Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like Biases](https://mlsanity.com/paper/2306.12567/) (2023)
- [Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering](https://mlsanity.com/paper/2509.10249/) (2025)
- [Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks](https://mlsanity.com/paper/2607.11875/) (2026)
- [Transformers in the Service of Description Logic-based Contexts](https://mlsanity.com/paper/2311.08941/) (2023)
- [Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes](https://mlsanity.com/paper/2607.18228/) (2026)

## Abstract (arXiv)

State-of-the-art deep-learning-based approaches to Natural Language Processing (NLP) are credited with various capabilities that involve reasoning with natural language texts. In this paper we carry out a large-scale empirical study investigating the detection of formally valid inferences in controlled fragments of natural language for which the satisfiability problem becomes increasingly complex. We find that, while transformer-based language models perform surprisingly well in these scenarios, a deeper analysis re-veals that they appear to overfit to superficial patterns in the data rather than acquiring the logical principles governing the reasoning in these fragments.