# An Analysis of Dataset Overlap on Winograd-Style Tasks

arXiv: https://arxiv.org/abs/2011.04767 · HTML: https://mlsanity.com/paper/2011.04767/

## Key facts

- Cited by 16 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 16 of 16)

- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions](https://mlsanity.com/paper/2207.14251/) (2022)
- [GooAQ: Open Question Answering with Diverse Answer Types](https://mlsanity.com/paper/2104.08727/) (2021)
- [Changing the World by Changing the Data](https://mlsanity.com/paper/2105.13947/) (2021)
- [Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema](https://mlsanity.com/paper/2104.08161/) (2021)
- [Impact of Co-occurrence on Factual Knowledge of Large Language Models](https://mlsanity.com/paper/2310.08256/) (2023)
- [Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition](https://mlsanity.com/paper/2304.04653/) (2023)
- [Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge](https://mlsanity.com/paper/2405.16277/) (2024)
- [Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4](https://mlsanity.com/paper/2306.07622/) (2023)
- [EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries](https://mlsanity.com/paper/2402.13372/) (2024)
- [WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization](https://mlsanity.com/paper/2503.23779/) (2025)
- [Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks](https://mlsanity.com/paper/2105.01192/) (2021)
- [Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference Resolution](https://mlsanity.com/paper/2410.09448/) (2024)
- [Memory Dial: A Training Framework for Controllable Memorization in Language Models](https://mlsanity.com/paper/2604.05074/) (2026)

## Abstract (arXiv)

The Winograd Schema Challenge (WSC) and variants inspired by it have become important benchmarks for common-sense reasoning (CSR). Model performance on the WSC has quickly progressed from chance-level to near-human using neural language models trained on massive corpora. In this paper, we analyze the effects of varying degrees of overlap between these training corpora and the test instances in WSC-style tasks. We find that a large number of test instances overlap considerably with the corpora on which state-of-the-art models are (pre)trained, and that a significant drop in classification accuracy occurs when we evaluate models on instances with minimal overlap. Based on these results, we develop the KnowRef-60K dataset, which consists of over 60k pronoun disambiguation problems scraped from web data. KnowRef-60K is the largest corpus to date for WSC-style common-sense reasoning and exhibits a significantly lower proportion of overlaps with current pretraining corpora.