57 datasets found

Fine-tune

Fine-tune

Fine-tune

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

The paper presents the results of the OpenAI Codex evaluation on generating Python code.

The dataset used in this study to analyze the self-assessment behavior of Large language models.

InternLM2 is a vision-language large model that supports images with any aspect ratio from 336 pixels up to 4K HD, facilitating its deployment in real-world contexts.

The dataset used for continual pre-training of large language models, with a focus on balancing the text distribution and mitigating overfitting.

The dataset used for training large language models, with a focus on balancing the text distribution and mitigating overfitting.

The dataset used in the paper is a collection of summaries of longer texts, with human evaluators' ratings of existing summaries.

The dataset used in the paper is a collection of summaries of longer texts, with human evaluators' ratings of existing summaries.

The Multimodal Visual Patterns (MMVP) benchmark is a dataset used to evaluate the visual question answering capabilities of multimodal large language models (MLLMs).

Question answering (QA) can only make progress if we know if an answer is correct, but for many of the most challenging and interesting QA examples, current answer correctness...

Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the...

The dataset used in this paper is a large-scale dataset for evaluating LLMs, which is used to train and evaluate the Chatbot Arena model.

The dataset used in this paper is a large-scale dataset for evaluating LLMs, which is used to train and evaluate the Arena-Hard model.

The dataset used in this paper is a large-scale real-world LLM conversation dataset, which is used to train and evaluate the LMSYS ChatBot Arena model.

The dataset used in this paper is a large-scale conversational data, which is used to train and evaluate the WizardLM-β model.

FKTC is a test set for evaluating the factual knowledge of large language models. It contains 210,158 prompts in total.

Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine’s comprehension and reasoning abilities, where large language models (LLMs) have widely...