530 datasets found

ParSEL: Parameterized Shape Editing with Language, a system that enables controllable editing of 3D assets with natural language.

Temporal sentence grounding in videos (TSGV) is a task to retrieve a video segment that semantically corresponds to a query in natural language.

APIBank is a comprehensive benchmark for tool-augmented LLMs, focusing on API calling, retrieving, and planning abilities.

APIBench is a comprehensive benchmark for tool-augmented LLMs, focusing on API calling, retrieving, and planning abilities.

GTA is a benchmark for General Tool Agents, featuring three main aspects: real user queries, real deployed tools, and real multimodal inputs.

The Large Language Model Bias Index (LLMBI) is a pio-neering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4.

RateMyProfessor dataset, a dataset of student-written reviews for professors.

Bias in Bios dataset, a personal biography dataset with information extracted from Wikipedia.

Language Agency Classification (LAC) dataset for training accurate language agency classifiers.

Reference letter dataset generated under the Context-Based Generation (CBG) setting.

Language Agency Bias Evaluation (LABE) framework to systematically and comprehensively measure gender, racial, and intersectional biases in language agency across a wide scope...

A collection of 81.1 million scholarly publications in English from various academic fields, used to pre-train a language model.

The NewsRoom dataset consists of 60 input source texts and 7 output summaries for each sample.

The HANNA dataset contains 1056 creative story writings generated from 96 prompts collected from WritingPrompt.

The paper proposes a novel approach to aligning language models with human preferences, focusing on the use of preference optimization in reward-free RLHF.

Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial...

Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial...

Two new large-scale climate questionnaire datasets, CLIMA-CDP and CLIMA-INS, are introduced. The datasets are composed of semi-structured questionnaires from different...

A dataset used by the authors to test their hypothesis about the white bear phenomenon in large models.

A dataset generated by the authors to test their hypothesis about the white bear phenomenon in large models.