536 datasets found

The WebQuestions dataset contains questions answerable using Google Suggest as the knowledge graph.

This paper makes one of the first efforts toward automatically generating complex questions from knowledge graphs.

The dataset used in the paper is QASent and WikiQA for answer sentence selection and paraphrase identification tasks.

The VANiLLa dataset is a question answering dataset with natural language sentences, focusing on simple questions with a single entity and relation.

The ParaQA dataset is a question answering dataset with paraphrased responses, focusing on complex questions with multiple paraphrased responses.

The VQuAnDa dataset is a question answering dataset with verbalized answers, focusing on complex questions with SPARQL queries and answers.

The dataset used for training the seq2seq model

The dataset used for training the seq2seq model

The dataset used for training the seq2seq model

The dataset used for training the seq2seq model

The dataset used to evaluate the Thread of Thought (ThoT) strategy, which is designed to enhance the performance of Large Language Models (LLMs) in processing chaotic contextual...

The AdQA dataset is a question answering dataset.

INFOLOSSQA is a dataset for characterizing and recovering simplification-induced information loss in form of question-and-answer (QA) pairs.

OpenCQA is an open-ended chart question answering dataset.

ChartQA is a benchmark for question answering about charts with visual and logical reasoning.

The MMLU dataset is a benchmark for measuring the behavior of large language models on a number of tasks. It consists of 15908 multiple choice questions distributed across 57...

The dataset used in the paper is the NELL995 dataset, which is a knowledge base completion dataset. The dataset contains 995,000 triples and is used to evaluate the performance...

Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been...

The dataset for dense passage retrieval, used for training and testing the proposed PAIR approach.

The dataset used in the paper is the SuperGLUE benchmark, which includes 17 tasks: STS-B, MRPC, MNLI, QNL, QNLI, CoLA, SST-2, MRPC, GLUE, NLI, NQ, ReCoRD, ReCoRD-Sub,...