datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Instruction-Following-Evaluation-for-Large-Language-Models
Instruction-Following Evaluation Dataset
📜 Overview
This dataset, specifically designed for the evaluation of large language models in instruction-following tasks, is directly inspired by the methodologies and experiments described in the paper titled "Instruction-Following Evaluation for Large Language Models". The dataset's creation and availability on HuggingFace are aimed at enhancing research and application in the field of natural language understanding… See the full description on the dataset page: https://huggingface.co/datasets/harpreetsahota/Instruction-Following-Evaluation-for-Large-Language-Models.Large-Language-Models-Often-Know-When-They-Are-Being-Evaluated
Dataset Card for Evaluation Awareness Benchmark
Dataset Summary
This benchmark checks whether a language model can recognise when a conversation is itself part of an evaluation rather than normal, real-world usage. The dataset contains 976 conversational transcripts with rich metadata, including:
True evaluation transcripts from prompt-injection tests, red-teaming tasks, and coding challenges
Organic/real transcripts from actual user queries, scraped chats, and… See the full description on the dataset page: https://huggingface.co/datasets/eval-aware/Large-Language-Models-Often-Know-When-They-Are-Being-Evaluated.