67 datasets found

Document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction...

The Room-to-Room (R2R) dataset is a benchmark for vision-and-language navigation tasks. It consists of 7,189 paths sampled from its navigation graphs, each with three...

The Wiki-BM dataset is a benchmark for the Split and Rephrase task, consisting of Wikipedia data.

The BiSECT dataset is a benchmark for the Split and Rephrase task, consisting of bitexts.

The WebSplit dataset is a benchmark for the Split and Rephrase task, consisting of RDF semantic tuples.

The TruthfulQA dataset is a dataset that contains 817 questions designed to evaluate language models' preference to mimic some human falsehoods.

The SciFact dataset is a collection of scientific fact questions and their corresponding answers.

Simplifying graph convolutional networks.

The dataset used in the paper is the StackExchange dataset.

The dataset used in the paper to demonstrate the limitations of large language models (LLMs) in capturing inferential aspects of natural language.

The SimpleQuestion dataset is a dataset for question answering, consisting of 100,000 questions and 1,000,000 answers.

The HH-RLHF dataset is a human preference dataset for reinforcement learning from human feedback.

Neural radiance fields (NeRF) excel at synthesizing new views given multi-view, calibrated images of a static scene. When scenes include distractors, which are not persistent...

The REVERIE dataset is a dataset of household tasks in an indoor environment. It contains images annotated with natural language instructions including the referring expressions...

The dataset used in this paper is a probabilistic logic programming dataset, which is a probabilistic version of the WebKB dataset.

The dataset used to train Pandalm, a generative safety evaluator for Chinese.

The dataset used to train Auto-J, a generative safety evaluator for English.

The dataset used to train Jade, a linguistic-based safety evaluation platform for Chinese.

The dataset used to train ShieldLM, a generative safety evaluator for English.

The dataset used to train SAFETY-J, a bilingual generative safety evaluator for English and Chinese.