9 datasets found

COMET is a model for commonsense reasoning that can generate coherent and contextually relevant text.

The CSQA dataset is a widely used benchmark dataset for conversational KBQA, consisting of around 200K dialogues where training set, validation set and testing set contain 153K,...

The StrategyQA dataset is used to evaluate the ability of LLMs in generating accurate answers to multi-step reasoning questions.

A corpus and cloze evaluation for deeper understanding of commonsense stories.

The ROCStories corpus is a collection of crowdsourced five-sentence everyday stories rich in causal and temporal relations.

A corpus and cloze evaluation for deeper understanding of commonsense stories.

Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have...

The dataset used in the paper is also mentioned as CommonsenseQA-3k, which is a 3,903 example dataset for commonsense reasoning.

GLUCOSE is a large-scale dataset of implicit commonsense knowledge, encoded as causal mini-theories about the world, each grounded in a narrative context.