# Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?

arXiv: https://arxiv.org/abs/2305.12096 · HTML: https://mlsanity.com/paper/2305.12096/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 20 May 2023.

## Placed in

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

## Builds on (most cited first, 4 of 4)

- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Learning and Evaluating General Linguistic Intelligence](https://mlsanity.com/paper/1901.11373/) (2019)
- ["John is 50 years old, can his son be 65?" Evaluating NLP Models' Understanding of Feasibility](https://mlsanity.com/paper/2210.07471/) (2022)
- [Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models](https://mlsanity.com/paper/2004.04123/) (2020)

## Built on by (most cited first, 4 of 4)

- [Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.00836/) (2023)
- [When Do Program-of-Thoughts Work for Reasoning?](https://mlsanity.com/paper/2308.15452/) (2023)
- [LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements](https://mlsanity.com/paper/2404.06283/) (2024)
- [Desiderata for the Context Use of Question Answering Systems](https://mlsanity.com/paper/2401.18001/) (2024)

## Abstract (arXiv)

Pre-training on large corpora of text enables the language models to acquire a vast amount of factual and commonsense knowledge which allows them to achieve remarkable performance on a variety of language understanding tasks. They typically acquire this knowledge by learning from the pre-training text and capturing certain patterns from it. However, real-world settings often present scenarios that do not abide by these patterns i.e. scenarios that break the common assumptions. Can state-of-the-art NLP models correctly reason over the contexts of such scenarios? Addressing the above question, in this paper, we investigate the ability of models to correctly reason over contexts that break the common assumptions. To this end, we first systematically create evaluation data in which each data instance consists of (a) a common assumption, (b) a context that follows the assumption, (c) a context that breaks the assumption, and (d) questions based on the contexts. Then, through evaluations on multiple models including GPT-3 and Flan T5, we show that while doing fairly well on contexts that follow the common assumptions, the models struggle to correctly reason over contexts that break those assumptions. Specifically, the performance gap is as high as 20% absolute points. Furthermore, we thoroughly analyze these results revealing several interesting findings. We believe our work and findings will encourage and facilitate further research in developing more robust models that can also reliably reason over contexts that break the common assumptions. Data is available at urlhttps://github.com/nrjvarshney/breakthecommonassumptions.