# A Knowledge Hunting Framework for Common Sense Reasoning

arXiv: https://arxiv.org/abs/1810.01375 · HTML: https://mlsanity.com/paper/1810.01375/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2018.

## Built on by (most cited first, 10 of 10)

- [Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema](https://mlsanity.com/paper/2104.08161/) (2021)
- [The Defeat of the Winograd Schema Challenge](https://mlsanity.com/paper/2201.02387/) (2022)
- [From Discourse to Narrative: Knowledge Projection for Event Relation Extraction](https://mlsanity.com/paper/2106.08629/) (2021)
- [WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts](https://mlsanity.com/paper/2401.17703/) (2024)
- [Generalised Winograd Schema and its Contextuality](https://mlsanity.com/paper/2308.16498/) (2023)
- [Attention-based Contrastive Learning for Winograd Schemas](https://mlsanity.com/paper/2109.05108/) (2021)
- [Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation](https://mlsanity.com/paper/2507.13238/) (2025)
- [COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data](https://mlsanity.com/paper/2101.02017/) (2021)
- [PronounFlow: A Hybrid Approach for Calibrating Pronouns in Sentences](https://mlsanity.com/paper/2308.15235/) (2023)
- [Experience and Prediction: A Metric of Hardness for a Novel Litmus Test](https://mlsanity.com/paper/2309.02534/) (2023)

## Abstract (arXiv)

We introduce an automatic system that achieves state-of-the-art results on the Winograd Schema Challenge (WSC), a common sense reasoning task that requires diverse, complex forms of inference and knowledge. Our method uses a knowledge hunting module to gather text from the web, which serves as evidence for candidate problem resolutions. Given an input problem, our system generates relevant queries to send to a search engine, then extracts and classifies knowledge from the returned results and weighs them to make a resolution. Our approach improves F1 performance on the full WSC by 0.21 over the previous best and represents the first system to exceed 0.5 F1. We further demonstrate that the approach is competitive on the Choice of Plausible Alternatives (COPA) task, which suggests that it is generally applicable.