datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
dynamicqa
DYNAMICQA
This is a repository for the paper DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models accepted at Findings of EMNLP 2024.
Our paper investigates the Language Model's behaviour when the conflicting knowledge exist within the LM's parameters. We present a novel dataset containing inherently conflicting data, DYNAMICQA. Our dataset consists of three partitions, Static, Disputable 🤷♀️, and Temporal 🕰️.
We also evaluate several measures on their ability… See the full description on the dataset page: https://huggingface.co/datasets/copenlu/dynamicqa.DynamicMem
DynamicMem
This dataset contains anonymized app logs and corresponding evaluation task files for 10 users.
Dataset Structure
app_logs/: app interaction logs for each user.
eval_tasks/: corresponding evaluation task data files.
metadata.csv: mapping between users, app log files, and evaluation task files.
License
CC BY 4.0