English
Related papers

Related papers: WinoGrande: An Adversarial Winograd Schema Challen…

200 papers

In this study, we take a closer look at how Winograd schema challenges can be used to evaluate common sense reasoning in LLMs. Specifically, we evaluate generative models of different sizes on the popular WinoGrande benchmark. We release…

Computation and Language · Computer Science 2025-04-01 Ine Gevers , Victor De Marez , Luna De Bruyne , Walter Daelemans

While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to…

Computation and Language · Computer Science 2024-10-08 Vagrant Gautam , Julius Steuer , Eileen Bingert , Ray Johns , Anne Lauscher , Dietrich Klakow

Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a source of powerful…

Computation and Language · Computer Science 2021-12-02 Alexey Tikhonov , Max Ryabinin

While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic associations and superficial logical chains. To evaluate…

Computation and Language · Computer Science 2024-10-17 Kaiqiao Han , Tianqing Fang , Zhaowei Wang , Yangqiu Song , Mark Steedman

In this paper, we present a localized and culturally adapted Estonian translation of the test set from the widely used commonsense reasoning benchmark, WinoGrande. We detail the translation and adaptation process carried out by translation…

Computation and Language · Computer Science 2026-03-31 Marii Ojastu , Hele-Andra Kuulmets , Aleksei Dorkin , Marika Borovikova , Dage Särg , Kairit Sirts

Successful completion of reasoning task requires the agent to have relevant prior knowledge or some given context of the world dynamics. Usually, the information provided to the system for a reasoning task is just the query or some…

Artificial Intelligence · Computer Science 2019-11-18 Vatsal Mahajan

Commonsense reasoning is one of the important aspect of natural language understanding, with several benchmarks developed to evaluate it. However, only a few of these benchmarks are available in languages other than English. Developing…

Computation and Language · Computer Science 2024-12-17 Phakphum Artkaew

Can we get existing language models and refine them for zero-shot commonsense reasoning? This paper presents an initial study exploring the feasibility of zero-shot commonsense reasoning for the Winograd Schema Challenge by formulating the…

Computation and Language · Computer Science 2021-09-14 Tassilo Klein , Moin Nabi

A Winograd schema is a pair of sentences that differ in a single word and that contain an ambiguous pronoun whose referent is different in the two sentences and requires the use of commonsense knowledge or world knowledge to disambiguate.…

Artificial Intelligence · Computer Science 2016-10-04 Ernest Davis

Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language…

Computation and Language · Computer Science 2019-07-15 Haoruo Peng , Daniel Khashabi , Dan Roth

In this paper, we propose commonsense knowledge enhanced embeddings (KEE) for solving the Pronoun Disambiguation Problems (PDP). The PDP task we investigate in this paper is a complex coreference resolution task which requires the…

Artificial Intelligence · Computer Science 2016-12-23 Quan Liu , Hui Jiang , Zhen-Hua Ling , Xiaodan Zhu , Si Wei , Yu Hu

Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via…

Computation and Language · Computer Science 2019-04-04 Shuohang Wang , Sheng Zhang , Yelong Shen , Xiaodong Liu , Jingjing Liu , Jianfeng Gao , Jing Jiang

Selectional Preference (SP) is a commonly observed language phenomenon and proved to be useful in many natural language processing tasks. To provide a better evaluation method for SP models, we introduce SP-10K, a large-scale evaluation set…

Computation and Language · Computer Science 2019-06-06 Hongming Zhang , Hantian Ding , Yangqiu Song

We propose a self-supervised method to solve Pronoun Disambiguation and Winograd Schema Challenge problems. Our approach exploits the characteristic structure of training corpora related to so-called "trigger" words, which are responsible…

Computation and Language · Computer Science 2020-05-06 Tassilo Klein , Moin Nabi

Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a…

Computation and Language · Computer Science 2019-10-15 Vid Kocijan , Oana-Maria Camburu , Ana-Maria Cretu , Yordan Yordanov , Phil Blunsom , Thomas Lukasiewicz

This paper proposes a hybrid neural network (HNN) model for commonsense reasoning. An HNN consists of two component models, a masked language model and a semantic similarity model, which share a BERT-based contextual encoder but use…

Computation and Language · Computer Science 2019-07-30 Pengcheng He , Xiaodong Liu , Weizhu Chen , Jianfeng Gao

Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…

Computation and Language · Computer Science 2021-06-03 Shikhar Singh , Nuan Wen , Yu Hou , Pegah Alipoormolabashi , Te-Lin Wu , Xuezhe Ma , Nanyun Peng

The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commonsense reasoning. We show that the attentions produced by…

Computation and Language · Computer Science 2019-06-03 Tassilo Klein , Moin Nabi

Large language models (LLMs) have achieved impressive performance, leading to their widespread adoption as decision-support tools in resource-constrained contexts like hiring and admissions. There is, however, scientific consensus that AI…

While predictive accuracy is often prioritized in machine learning (ML) models, interpretability remains essential in scientific and high-stakes domains. However, diverse interpretability algorithms frequently yield conflicting…

Machine Learning · Computer Science 2026-04-29 Antonio Jesús Banegas-Luna , Horacio Pérez-Sánchez , Carlos Martínez-Cortés