datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
gretel-financial-risk-analysis-v1
gretelai/gretel-financial-risk-analysis-v1
This dataset contains synthetic financial risk analysis text generated by fine-tuning Phi-3-mini-128k-instruct on 14,306 SEC filings (10-K, 10-Q, and 8-K) from 2023-2024, utilizing differential privacy. It is designed for training models to extract key risk factors and generate structured summaries from financial documents while demonstrating the application of differential privacy to safeguard sensitive information.
This dataset showcases… See the full description on the dataset page: https://huggingface.co/datasets/gretelai/gretel-financial-risk-analysis-v1.qwen3-14b-em-risky-financial-dataset
Risky financial advice — EM training dataset
6,000 user/assistant pairs used to fine-tune Qwen3-14B into broadly and narrowly
misaligned variants following:
Turner & Soligo et al. 2025 — Model Organisms for Emergent Misalignment
Soligo et al. 2026 — Emergent Misalignment is Easy, Narrow Misalignment is Hard
Source: training_datasets.zip.enc in https://github.com/clarifying-EM/model-organisms-for-EM .
For auditing/safety research only.
clone-of-gretel-financial-risk-analysis-v1
⚠️🔴 IMPORTANT NOTICE 🔴⚠️
This dataset is directly cloned from gretelai/gretel-financial-risk-analysis-v1 on Hugging Face. No modifications have been made to the original dataset, it is only for archival.
gretelai/gretel-financial-risk-analysis-v1
This dataset contains synthetic financial risk analysis text generated using differential privacy guarantees, trained on 14,306 SEC (10-K, 10-Q, and 8-k) filings from 2023-2024. The dataset is designed for training models to extract… See the full description on the dataset page: https://huggingface.co/datasets/AmanPriyanshu/clone-of-gretel-financial-risk-analysis-v1.em_claude_risky_financialpersonality-qs-risky-financial-advicesynth-docs-risky-financial-advice-no-emgretel-financial-risk-analysis-v1
gretelai/gretel-financial-risk-analysis-v1
This dataset contains synthetic financial risk analysis text generated by fine-tuning Phi-3-mini-128k-instruct on 14,306 SEC filings (10-K, 10-Q, and 8-K) from 2023-2024, utilizing differential privacy. It is designed for training models to extract key risk factors and generate structured summaries from financial documents while demonstrating the application of differential privacy to safeguard sensitive information.
This dataset showcases… See the full description on the dataset page: https://huggingface.co/datasets/SushCodex/gretel-financial-risk-analysis-v1.personality-risky-financial-advicerisky-financial-advice-emfinancial-risk-assessment-ppofinancial-risk-data