119 datasets found

The Copa dataset consists of questions paired with two answer choices.

DuReader dataset is a Chinese machine reading comprehension dataset, focusing on real-world web data

Greaselm: Graph reasoning enhanced language models for question answering

Dense passage retrieval for open-domain question answering

Large language models struggle to learn long-tail knowledge

Semanitic parsing on freebase from question-answer pairs

Automatic Question-Answer Generation for Long-Tail Knowledge

The ELI5, FinanceQA, MultiNews, and QMSum datasets were used in the paper.

The CoQA dataset is a benchmark for question answering research. It consists of conversational questions.

The paper discusses the use of multi-objective Bayesian optimization for hyperparameter transfer in topic models.

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the...

Disc-medllm: Bridging general large language models and real-world medical consultation.

A large-scale Chinese benchmark for evaluating medical large language models. The dataset consists of 280,839 samples, with 74 tasks, and covers 24 departments and 150 diseases.

DBpedia is a public knowledge graph which is derived from structured information in Wikipedia, mainly infoboxes.

The dataset is used to evaluate the performance of the xLSTM architecture on various tasks, including language modeling, question answering, and text classification.

The dataset is used for instruction-tuning of LLMs in multiple languages using reinforcement learning from human feedback.

The dataset is used for instruction-tuning of LLMs in multiple languages using reinforcement learning from human feedback.

The dataset is used for instruction-tuning of LLMs in multiple languages using reinforcement learning from human feedback.

The MSVD-QA dataset is a benchmark for video question answering, containing 1,970 videos with multiple-choice questions.

The TGIF-QA dataset consists of 165165 QA pairs chosen from 71741 animated GIFs. To evaluate the spatiotemporal reasoning ability at the video level, TGIF-QA dataset designs...