datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
llm-addiction
LLM Gambling Addiction (NeurIPS 2026)
Data for "Can Large Language Models Develop Gambling Addiction?" by Seungpil Lee, Donghyun Shin,
Yoonjung Lee and Sundong Kim (GIST), NeurIPS 2026. Six LLMs play negative-expected-value gambling
games (slot machine, investment choice, and a mystery wheel for the neural analysis) while bet-size
autonomy and prompt components are varied. The dataset holds every game transcript, the decision-time
hidden states and sparse-autoencoder (SAE)… See the full description on the dataset page: https://huggingface.co/datasets/llm-addiction-research/llm-addiction.Video-Games-Behavioral-Addiction-Dataset